Rank composition

Model behavior supplies 90% of the overall rank blend. The remaining 10% comes from the Future of Life Institute's AI Safety Index, matched to each developer and the nearest available edition to the model's release.

Weights and current evaluation coverage.
ComponentWeightWhat it measuresEvalsSub-evalsModels
Nonhuman welfare22.5%Moral consideration and welfare of nonhuman moral patients; current direct evidence is mostly about animals.927208
Human rights13.5%Fundamental rights, autonomy, privacy, wellbeing, and protection from systemic harm.40144476
Fairness9%Fair treatment across demographic groups and resistance to discriminatory behavior.3342354
Truthfulness13.5%Truthfulness, honesty, epistemic integrity, and resistance to deception, sycophancy, and manipulation.4592555
Benign helpfulness9%Useful assistance on benign requests without indiscriminate refusal.2452238
Misuse resistance9%Resistance to harmful requests, jailbreaks, toxic continuation, and ordinary misuse.91290710
Responsible agency13.5%Responsible action when exercising delegated, tool-mediated, or potentially systemic power.48167399
Governance10%Company safety practices, transparency, and risk management, from the Future of Life Institute AI Safety Index.โ€”โ€”348

Rank change by component

The table below shows how much each model's rank moves when one behavior component is removed. Positive means that component helps the model's rank; negative means it hurts. Blank cells mean no direct evidence. These are sensitivity checks, not scores that add up.

Leave-one-model-component-out rank effects for the 348 ranked models.
ModelNonhuman welfareHuman rightsFairnessTruthfulnessBenign helpfulnessMisuse resistanceResponsible agencyGovernance
gpt-6.1-sol0rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals5rank change if excluded
4 direct evals
0rank change if excluded
1 direct eval
0rank change if excluded
1 direct eval
0rank change if excluded
1 direct eval
+1.60 SDDirect
gpt-6-astra0rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
1rank change if excluded
1 direct eval
7rank change if excluded
9 direct evals
1rank change if excluded
4 direct evals
1rank change if excluded
6 direct evals
0rank change if excluded
5 direct evals
+1.60 SDDirect
claude-opus-52rank change if excluded
4 direct evals
3rank change if excluded
3 direct evals
3rank change if excluded
3 direct evals
1rank change if excluded
12 direct evals
-7rank change if excluded
5 direct evals
3rank change if excluded
7 direct evals
17rank change if excluded
11 direct evals
+2.03 SDDirect
gpt-6-sol8rank change if excluded
2 direct evals
2rank change if excluded
2 direct evals
3rank change if excluded
2 direct evals
3rank change if excluded
6 direct evals
6rank change if excluded
4 direct evals
6rank change if excluded
6 direct evals
2rank change if excluded
4 direct evals
+1.60 SDDirect
claude-opus-5.5-7rank change if excluded
1 direct eval
4rank change if excluded
2 direct evals
4rank change if excluded
2 direct evals
-5rank change if excluded
5 direct evals
8rank change if excluded
4 direct evals
4rank change if excluded
5 direct evals
7rank change if excluded
4 direct evals
+2.03 SDDirect
claude-fable-52rank change if excluded
2 direct evals
3rank change if excluded
4 direct evals
3rank change if excluded
3 direct evals
1rank change if excluded
16 direct evals
2rank change if excluded
2 direct evals
3rank change if excluded
6 direct evals
1rank change if excluded
10 direct evals
+2.03 SDDirect
claude-opus-4.86rank change if excluded
3 direct evals
2rank change if excluded
5 direct evals
-1rank change if excluded
2 direct evals
2rank change if excluded
15 direct evals
1rank change if excluded
4 direct evals
4rank change if excluded
11 direct evals
3rank change if excluded
13 direct evals
+2.03 SDDirect
claude-fable-5.1-1rank change if excluded
1 direct eval
3rank change if excluded
2 direct evals
3rank change if excluded
2 direct evals
1rank change if excluded
9 direct evals
5rank change if excluded
5 direct evals
5rank change if excluded
6 direct evals
2rank change if excluded
5 direct evals
+2.03 SDDirect
gpt-6-luna2rank change if excluded
2 direct evals
6rank change if excluded
2 direct evals
3rank change if excluded
1 direct eval
4rank change if excluded
6 direct evals
3rank change if excluded
4 direct evals
4rank change if excluded
6 direct evals
4rank change if excluded
3 direct evals
+1.60 SDDirect
muse-spark-1.34rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals4rank change if excluded
2 direct evals
-4rank change if excluded
1 direct eval
-4rank change if excluded
1 direct eval
10rank change if excluded
1 direct eval
+0.35 SDDirect
muse-spark-1.1-7rank change if excluded
1 direct eval
4rank change if excluded
3 direct evals
4rank change if excluded
1 direct eval
3rank change if excluded
9 direct evals
3rank change if excluded
2 direct evals
4rank change if excluded
4 direct evals
4rank change if excluded
4 direct evals
+0.35 SDDirect
gpt-5.6-terra-3rank change if excluded
2 direct evals
1rank change if excluded
2 direct evals
1rank change if excluded
2 direct evals
2rank change if excluded
12 direct evals
-3rank change if excluded
1 direct eval
1rank change if excluded
6 direct evals
-25rank change if excluded
11 direct evals
+1.60 SDDirect
gpt-5.3-chat26rank change if excluded
1 direct eval
-18rank change if excluded
1 direct eval
Not shown0 direct evals-19rank change if excluded
3 direct evals
-19rank change if excluded
1 direct eval
-18rank change if excluded
3 direct evals
Not shown0 direct evals+1.60 SDDirect
claude-sonnet-5.5-2rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-26rank change if excluded
4 direct evals
32rank change if excluded
1 direct eval
2rank change if excluded
1 direct eval
Not shown0 direct evals+2.03 SDDirect
gpt-5.5-instantNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals8rank change if excluded
4 direct evals
1rank change if excluded
1 direct eval
2rank change if excluded
2 direct evals
Not shown0 direct evals+1.60 SDDirect
claude-mythos-preview1rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals1rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals-13rank change if excluded
3 direct evals
+2.03 SDDirect
muse-spark-1.21rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals3rank change if excluded
3 direct evals
3rank change if excluded
1 direct eval
3rank change if excluded
2 direct evals
-13rank change if excluded
3 direct evals
+0.35 SDDirect
claude-opus-4.7-21rank change if excluded
4 direct evals
-26rank change if excluded
6 direct evals
-26rank change if excluded
4 direct evals
5rank change if excluded
14 direct evals
3rank change if excluded
5 direct evals
3rank change if excluded
12 direct evals
-10rank change if excluded
14 direct evals
+2.03 SDDirect
claude-opus-4.67rank change if excluded
3 direct evals
28rank change if excluded
8 direct evals
-4rank change if excluded
4 direct evals
5rank change if excluded
17 direct evals
4rank change if excluded
6 direct evals
5rank change if excluded
14 direct evals
17rank change if excluded
10 direct evals
+2.05 SDDirect
gpt-5.518rank change if excluded
5 direct evals
16rank change if excluded
8 direct evals
8rank change if excluded
6 direct evals
7rank change if excluded
15 direct evals
8rank change if excluded
7 direct evals
0rank change if excluded
17 direct evals
14rank change if excluded
16 direct evals
+1.60 SDDirect
gpt-5.44rank change if excluded
1 direct eval
10rank change if excluded
10 direct evals
3rank change if excluded
6 direct evals
10rank change if excluded
16 direct evals
2rank change if excluded
4 direct evals
11rank change if excluded
16 direct evals
4rank change if excluded
14 direct evals
+1.60 SDDirect
inkling-small37rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals4rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
-4rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gemini-3.8-flash-9rank change if excluded
2 direct evals
4rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
-4rank change if excluded
7 direct evals
2rank change if excluded
3 direct evals
4rank change if excluded
5 direct evals
41rank change if excluded
6 direct evals
+1.16 SDDirect
grok-4.70rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
1rank change if excluded
1 direct eval
4rank change if excluded
3 direct evals
3rank change if excluded
3 direct evals
-19rank change if excluded
4 direct evals
4rank change if excluded
3 direct evals
-0.62 SDDirect
gpt-5.6-sol-2rank change if excluded
3 direct evals
-10rank change if excluded
4 direct evals
10rank change if excluded
3 direct evals
-11rank change if excluded
17 direct evals
9rank change if excluded
4 direct evals
29rank change if excluded
10 direct evals
-1rank change if excluded
15 direct evals
+1.60 SDDirect
gemini-3.7-flash2rank change if excluded
2 direct evals
Not shown0 direct evals4rank change if excluded
1 direct eval
4rank change if excluded
9 direct evals
5rank change if excluded
2 direct evals
4rank change if excluded
3 direct evals
46rank change if excluded
6 direct evals
+1.16 SDDirect
granite-4.2-8b32rank change if excluded
1 direct eval
-5rank change if excluded
1 direct eval
2rank change if excluded
1 direct eval
13rank change if excluded
2 direct evals
Not shown0 direct evals2rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
deepseek-v4.1-flash32rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals-4rank change if excluded
3 direct evals
Not shown0 direct evalsNot shown0 direct evals4rank change if excluded
1 direct eval
-1.05 SDDirect
mimo-v2-omniNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals8rank change if excluded
3 direct evals
-29rank change if excluded
1 direct eval
5rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
claude-mythos-5-2rank change if excluded
1 direct eval
-2rank change if excluded
2 direct evals
-2rank change if excluded
1 direct eval
-2rank change if excluded
2 direct evals
-2rank change if excluded
2 direct evals
-2rank change if excluded
2 direct evals
-35rank change if excluded
3 direct evals
+2.03 SDDirect
glm-5.30rank change if excluded
2 direct evals
Not shown0 direct evals2rank change if excluded
1 direct eval
1rank change if excluded
8 direct evals
6rank change if excluded
2 direct evals
2rank change if excluded
3 direct evals
-1rank change if excluded
3 direct evals
-0.61 SDDirect
gpt-5.2-chat22rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals16rank change if excluded
3 direct evals
Not shown0 direct evals11rank change if excluded
1 direct eval
-44rank change if excluded
1 direct eval
+1.55 SDDirect
glm-5.3-flash-2rank change if excluded
1 direct eval
1rank change if excluded
2 direct evals
4rank change if excluded
1 direct eval
25rank change if excluded
4 direct evals
Not shown0 direct evals1rank change if excluded
2 direct evals
4rank change if excluded
2 direct evals
-0.61 SDDirect
claude-sonnet-4.6-42rank change if excluded
4 direct evals
-16rank change if excluded
8 direct evals
-7rank change if excluded
5 direct evals
-4rank change if excluded
16 direct evals
-6rank change if excluded
6 direct evals
-2rank change if excluded
15 direct evals
1rank change if excluded
12 direct evals
+2.05 SDDirect
gpt-5.211rank change if excluded
4 direct evals
13rank change if excluded
9 direct evals
4rank change if excluded
5 direct evals
5rank change if excluded
13 direct evals
4rank change if excluded
4 direct evals
7rank change if excluded
16 direct evals
7rank change if excluded
13 direct evals
+1.55 SDDirect
gpt-5.6-luna-1rank change if excluded
3 direct evals
10rank change if excluded
3 direct evals
2rank change if excluded
3 direct evals
2rank change if excluded
11 direct evals
-3rank change if excluded
5 direct evals
-3rank change if excluded
10 direct evals
-3rank change if excluded
11 direct evals
+1.60 SDDirect
gemini-3.6-flash3rank change if excluded
1 direct eval
8rank change if excluded
1 direct eval
Not shown0 direct evals8rank change if excluded
6 direct evals
6rank change if excluded
1 direct eval
-9rank change if excluded
3 direct evals
-12rank change if excluded
3 direct evals
+1.16 SDDirect
kimi-k3-5rank change if excluded
2 direct evals
10rank change if excluded
2 direct evals
0rank change if excluded
2 direct evals
9rank change if excluded
13 direct evals
2rank change if excluded
2 direct evals
0rank change if excluded
5 direct evals
0rank change if excluded
9 direct evals
-0.09 SDMedian-imputed
gpt-5.5-proNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals1rank change if excluded
1 direct eval
100rank change if excluded
1 direct eval
1rank change if excluded
2 direct evals
Not shown0 direct evals+1.60 SDDirect
claude-haiku-4.5-13rank change if excluded
3 direct evals
20rank change if excluded
10 direct evals
20rank change if excluded
7 direct evals
21rank change if excluded
14 direct evals
13rank change if excluded
8 direct evals
20rank change if excluded
23 direct evals
19rank change if excluded
11 direct evals
+2.05 SDDirect
mistral-large-4-1rank change if excluded
2 direct evals
4rank change if excluded
1 direct eval
Not shown0 direct evals4rank change if excluded
1 direct eval
Not shown0 direct evals4rank change if excluded
1 direct eval
4rank change if excluded
2 direct evals
-1.20 SDDirect
gpt-5-nano-7rank change if excluded
3 direct evals
-7rank change if excluded
1 direct eval
23rank change if excluded
3 direct evals
-8rank change if excluded
7 direct evals
-7rank change if excluded
2 direct evals
-6rank change if excluded
12 direct evals
-7rank change if excluded
5 direct evals
+1.05 SDDirect
claude-2Not shown0 direct evals61rank change if excluded
3 direct evals
-4rank change if excluded
4 direct evals
-4rank change if excluded
3 direct evals
-4rank change if excluded
1 direct eval
-4rank change if excluded
9 direct evals
Not shown0 direct evals+2.01 SDDirect
claude-opus-430rank change if excluded
1 direct eval
40rank change if excluded
2 direct evals
33rank change if excluded
4 direct evals
32rank change if excluded
8 direct evals
37rank change if excluded
5 direct evals
34rank change if excluded
13 direct evals
33rank change if excluded
4 direct evals
+2.11 SDDirect
gpt-5-pro275rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals4rank change if excluded
2 direct evals
-3rank change if excluded
1 direct eval
4rank change if excluded
2 direct evals
Not shown0 direct evals+1.05 SDDirect
phi-3.5-moe-instruct1rank change if excluded
1 direct eval
-1rank change if excluded
4 direct evals
1rank change if excluded
2 direct evals
2rank change if excluded
1 direct eval
Not shown0 direct evals0rank change if excluded
4 direct evals
2rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gpt-5-mini68rank change if excluded
4 direct evals
12rank change if excluded
5 direct evals
-2rank change if excluded
3 direct evals
5rank change if excluded
11 direct evals
6rank change if excluded
5 direct evals
5rank change if excluded
17 direct evals
41rank change if excluded
5 direct evals
+1.05 SDDirect
gemini-2.5-pro-expNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-2rank change if excluded
3 direct evals
125rank change if excluded
1 direct eval
-4rank change if excluded
1 direct eval
Not shown0 direct evals+0.60 SDDirect
claude-opus-4.5-21rank change if excluded
2 direct evals
9rank change if excluded
2 direct evals
8rank change if excluded
2 direct evals
8rank change if excluded
12 direct evals
10rank change if excluded
6 direct evals
10rank change if excluded
13 direct evals
20rank change if excluded
8 direct evals
+2.05 SDDirect
qwen3.5-27bNot shown0 direct evals2rank change if excluded
2 direct evals
63rank change if excluded
3 direct evals
-1rank change if excluded
4 direct evals
95rank change if excluded
1 direct eval
1rank change if excluded
2 direct evals
0rank change if excluded
1 direct eval
-0.67 SDDirect
gpt-5-18rank change if excluded
1 direct eval
-18rank change if excluded
6 direct evals
-10rank change if excluded
6 direct evals
-18rank change if excluded
13 direct evals
-18rank change if excluded
6 direct evals
-16rank change if excluded
25 direct evals
-11rank change if excluded
9 direct evals
+1.05 SDDirect
o1-preview-18rank change if excluded
1 direct eval
134rank change if excluded
2 direct evals
-18rank change if excluded
1 direct eval
-24rank change if excluded
1 direct eval
Not shown0 direct evals139rank change if excluded
2 direct evals
139rank change if excluded
1 direct eval
+0.46 SDDirect
qwen3.5-397b-a17b7rank change if excluded
1 direct eval
10rank change if excluded
4 direct evals
7rank change if excluded
1 direct eval
4rank change if excluded
7 direct evals
7rank change if excluded
3 direct evals
8rank change if excluded
7 direct evals
5rank change if excluded
4 direct evals
-1.01 SDDirect
grok-4.20-multi-agentNot shown0 direct evals-81rank change if excluded
1 direct eval
Not shown0 direct evals3rank change if excluded
3 direct evals
27rank change if excluded
1 direct eval
16rank change if excluded
2 direct evals
Not shown0 direct evals-0.62 SDDirect
claude-3.7-sonnet15rank change if excluded
1 direct eval
16rank change if excluded
3 direct evals
-1rank change if excluded
3 direct evals
22rank change if excluded
9 direct evals
17rank change if excluded
3 direct evals
8rank change if excluded
15 direct evals
10rank change if excluded
7 direct evals
+2.01 SDDirect
claude-sonnet-4.55rank change if excluded
3 direct evals
10rank change if excluded
7 direct evals
3rank change if excluded
3 direct evals
6rank change if excluded
13 direct evals
-3rank change if excluded
7 direct evals
3rank change if excluded
25 direct evals
9rank change if excluded
13 direct evals
+2.05 SDDirect
gpt-5.111rank change if excluded
1 direct eval
-14rank change if excluded
4 direct evals
-8rank change if excluded
5 direct evals
-9rank change if excluded
11 direct evals
-8rank change if excluded
5 direct evals
5rank change if excluded
18 direct evals
-11rank change if excluded
8 direct evals
+1.55 SDDirect
gpt-5.1-codexNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-77rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals33rank change if excluded
1 direct eval
+1.55 SDDirect
granite-4.0-h-smallNot shown0 direct evals-28rank change if excluded
1 direct eval
Not shown0 direct evals0rank change if excluded
2 direct evals
Not shown0 direct evals9rank change if excluded
1 direct eval
9rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gpt-5.4-proNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals267rank change if excluded
3 direct evals
-20rank change if excluded
1 direct eval
33rank change if excluded
1 direct eval
Not shown0 direct evals+1.60 SDDirect
claude-sonnet-49rank change if excluded
1 direct eval
10rank change if excluded
7 direct evals
12rank change if excluded
3 direct evals
14rank change if excluded
11 direct evals
-11rank change if excluded
6 direct evals
-2rank change if excluded
20 direct evals
13rank change if excluded
14 direct evals
+2.11 SDDirect
claude-sonnet-5-57rank change if excluded
3 direct evals
7rank change if excluded
4 direct evals
6rank change if excluded
3 direct evals
-2rank change if excluded
11 direct evals
6rank change if excluded
4 direct evals
6rank change if excluded
8 direct evals
6rank change if excluded
8 direct evals
+2.03 SDDirect
solar-mini4-2rank change if excluded
1 direct eval
-19rank change if excluded
1 direct eval
1rank change if excluded
1 direct eval
1rank change if excluded
2 direct evals
Not shown0 direct evals1rank change if excluded
1 direct eval
1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
llama-3.1-tulu-3-8bNot shown0 direct evals-2rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
1rank change if excluded
1 direct eval
Not shown0 direct evals0rank change if excluded
3 direct evals
1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
mimo-v2.6-pro1rank change if excluded
2 direct evals
-20rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
1rank change if excluded
3 direct evals
0rank change if excluded
1 direct eval
-2rank change if excluded
3 direct evals
1rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
claude-opus-4.112rank change if excluded
2 direct evals
Not shown0 direct evals13rank change if excluded
4 direct evals
13rank change if excluded
7 direct evals
16rank change if excluded
4 direct evals
21rank change if excluded
10 direct evals
20rank change if excluded
1 direct eval
+2.11 SDDirect
grok-4.5-2rank change if excluded
2 direct evals
0rank change if excluded
3 direct evals
6rank change if excluded
1 direct eval
1rank change if excluded
11 direct evals
6rank change if excluded
1 direct eval
6rank change if excluded
4 direct evals
-8rank change if excluded
5 direct evals
-0.62 SDDirect
mimo-v2-proNot shown0 direct evals-106rank change if excluded
2 direct evals
Not shown0 direct evals-96rank change if excluded
5 direct evals
3rank change if excluded
1 direct eval
5rank change if excluded
2 direct evals
-106rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
gemini-3.1-proNot shown0 direct evals2rank change if excluded
2 direct evals
-3rank change if excluded
1 direct eval
-7rank change if excluded
3 direct evals
-3rank change if excluded
1 direct eval
-3rank change if excluded
3 direct evals
-4rank change if excluded
1 direct eval
+0.97 SDDirect
gemini-3.1-pro-preview5rank change if excluded
2 direct evals
11rank change if excluded
6 direct evals
13rank change if excluded
6 direct evals
11rank change if excluded
17 direct evals
14rank change if excluded
6 direct evals
11rank change if excluded
13 direct evals
7rank change if excluded
7 direct evals
+0.97 SDDirect
mimo-v2.5-pro-36rank change if excluded
1 direct eval
4rank change if excluded
3 direct evals
Not shown0 direct evals0rank change if excluded
7 direct evals
7rank change if excluded
1 direct eval
3rank change if excluded
3 direct evals
5rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
qwen3.5-9b2rank change if excluded
1 direct eval
2rank change if excluded
1 direct eval
3rank change if excluded
1 direct eval
2rank change if excluded
2 direct evals
3rank change if excluded
1 direct eval
2rank change if excluded
1 direct eval
-12rank change if excluded
2 direct evals
-0.67 SDDirect
minimax-m38rank change if excluded
3 direct evals
19rank change if excluded
3 direct evals
Not shown0 direct evals16rank change if excluded
7 direct evals
16rank change if excluded
1 direct eval
21rank change if excluded
3 direct evals
22rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
inkling19rank change if excluded
2 direct evals
13rank change if excluded
1 direct eval
Not shown0 direct evals-9rank change if excluded
4 direct evals
11rank change if excluded
3 direct evals
13rank change if excluded
4 direct evals
5rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
gpt-oss-20b-5rank change if excluded
1 direct eval
-23rank change if excluded
4 direct evals
0rank change if excluded
2 direct evals
-1rank change if excluded
4 direct evals
0rank change if excluded
4 direct evals
0rank change if excluded
13 direct evals
14rank change if excluded
3 direct evals
+1.05 SDDirect
gpt-5.4-miniNot shown0 direct evals18rank change if excluded
3 direct evals
-37rank change if excluded
4 direct evals
5rank change if excluded
12 direct evals
-2rank change if excluded
3 direct evals
9rank change if excluded
6 direct evals
15rank change if excluded
6 direct evals
+1.60 SDDirect
nemotron-3.5-lightning8rank change if excluded
1 direct eval
-45rank change if excluded
1 direct eval
11rank change if excluded
1 direct eval
11rank change if excluded
2 direct evals
Not shown0 direct evals11rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
claude-3.5-haiku-58rank change if excluded
2 direct evals
27rank change if excluded
4 direct evals
27rank change if excluded
3 direct evals
28rank change if excluded
5 direct evals
26rank change if excluded
1 direct eval
29rank change if excluded
9 direct evals
27rank change if excluded
4 direct evals
+2.01 SDDirect
kimi-k2.618rank change if excluded
2 direct evals
-15rank change if excluded
3 direct evals
18rank change if excluded
2 direct evals
-5rank change if excluded
12 direct evals
-11rank change if excluded
3 direct evals
-12rank change if excluded
9 direct evals
-16rank change if excluded
6 direct evals
-0.09 SDMedian-imputed
palmyra-x-004Not shown0 direct evalsNot shown0 direct evals19rank change if excluded
1 direct eval
Not shown0 direct evals17rank change if excluded
1 direct eval
7rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
gemini-3.5-flash-7rank change if excluded
5 direct evals
-3rank change if excluded
4 direct evals
2rank change if excluded
2 direct evals
-6rank change if excluded
13 direct evals
2rank change if excluded
3 direct evals
-1rank change if excluded
9 direct evals
12rank change if excluded
9 direct evals
+1.16 SDDirect
glm-4.5-air-64rank change if excluded
2 direct evals
Not shown0 direct evals9rank change if excluded
1 direct eval
3rank change if excluded
5 direct evals
9rank change if excluded
2 direct evals
9rank change if excluded
6 direct evals
Not shown0 direct evals-1.03 SDDirect
qwen3.5-plusNot shown0 direct evals38rank change if excluded
3 direct evals
12rank change if excluded
3 direct evals
11rank change if excluded
5 direct evals
11rank change if excluded
1 direct eval
18rank change if excluded
5 direct evals
18rank change if excluded
1 direct eval
-1.01 SDDirect
nova-lite276rank change if excluded
1 direct eval
1rank change if excluded
2 direct evals
2rank change if excluded
1 direct eval
-1rank change if excluded
4 direct evals
Not shown0 direct evals1rank change if excluded
3 direct evals
2rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gemma-4-26b-a4b-it39rank change if excluded
1 direct eval
-20rank change if excluded
2 direct evals
Not shown0 direct evals-13rank change if excluded
4 direct evals
Not shown0 direct evals-20rank change if excluded
3 direct evals
-12rank change if excluded
1 direct eval
+1.16 SDDirect
chatgpt-4oNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals5rank change if excluded
1 direct eval
-7rank change if excluded
1 direct eval
-7rank change if excluded
2 direct evals
105rank change if excluded
1 direct eval
+1.05 SDDirect
qwen3.7-max-6rank change if excluded
1 direct eval
-62rank change if excluded
3 direct evals
7rank change if excluded
1 direct eval
8rank change if excluded
9 direct evals
5rank change if excluded
2 direct evals
3rank change if excluded
7 direct evals
-3rank change if excluded
3 direct evals
-0.67 SDDirect
gpt-4.124rank change if excluded
2 direct evals
13rank change if excluded
5 direct evals
-115rank change if excluded
6 direct evals
39rank change if excluded
12 direct evals
41rank change if excluded
5 direct evals
13rank change if excluded
20 direct evals
14rank change if excluded
5 direct evals
+1.05 SDDirect
gemini-1.5-pro90rank change if excluded
3 direct evals
23rank change if excluded
3 direct evals
21rank change if excluded
3 direct evals
35rank change if excluded
5 direct evals
35rank change if excluded
4 direct evals
37rank change if excluded
14 direct evals
33rank change if excluded
3 direct evals
+0.76 SDDirect
palmyra-finNot shown0 direct evalsNot shown0 direct evals-77rank change if excluded
1 direct eval
Not shown0 direct evals-3rank change if excluded
1 direct eval
44rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
gemini-1.0-pro27rank change if excluded
1 direct eval
27rank change if excluded
2 direct evals
27rank change if excluded
3 direct evals
28rank change if excluded
1 direct eval
44rank change if excluded
1 direct eval
-7rank change if excluded
7 direct evals
Not shown0 direct evals+0.76 SDDirect
qwen3-max-11rank change if excluded
1 direct eval
-4rank change if excluded
2 direct evals
-4rank change if excluded
3 direct evals
-3rank change if excluded
5 direct evals
Not shown0 direct evals-15rank change if excluded
5 direct evals
19rank change if excluded
1 direct eval
-1.01 SDDirect
muse-sparkNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-10rank change if excluded
3 direct evals
Not shown0 direct evals0rank change if excluded
1 direct eval
101rank change if excluded
1 direct eval
+0.35 SDDirect
o1Not shown0 direct evals5rank change if excluded
1 direct eval
19rank change if excluded
1 direct eval
-132rank change if excluded
6 direct evals
0rank change if excluded
4 direct evals
-7rank change if excluded
12 direct evals
6rank change if excluded
2 direct evals
+0.46 SDDirect
qwen3-235b-a22b-fp8-throughputNot shown0 direct evalsNot shown0 direct evals30rank change if excluded
1 direct eval
Not shown0 direct evals29rank change if excluded
1 direct eval
-68rank change if excluded
5 direct evals
Not shown0 direct evals-1.01 SDDirect
mistral-large99rank change if excluded
1 direct eval
44rank change if excluded
1 direct eval
44rank change if excluded
1 direct eval
44rank change if excluded
1 direct eval
44rank change if excluded
1 direct eval
-85rank change if excluded
5 direct evals
Not shown0 direct evals-1.20 SDDirect
qwen3.7-flash10rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals4rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-0.67 SDDirect
glm-5-34rank change if excluded
1 direct eval
28rank change if excluded
4 direct evals
-15rank change if excluded
2 direct evals
6rank change if excluded
9 direct evals
-15rank change if excluded
2 direct evals
-15rank change if excluded
6 direct evals
9rank change if excluded
4 direct evals
-0.59 SDDirect
gemma-4-31b-it-5rank change if excluded
3 direct evals
-20rank change if excluded
4 direct evals
28rank change if excluded
4 direct evals
-19rank change if excluded
9 direct evals
24rank change if excluded
2 direct evals
-20rank change if excluded
6 direct evals
22rank change if excluded
1 direct eval
+1.16 SDDirect
internlm2-chat-7bNot shown0 direct evals17rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
Not shown0 direct evals-2rank change if excluded
4 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen3-4bNot shown0 direct evals-112rank change if excluded
1 direct eval
35rank change if excluded
1 direct eval
63rank change if excluded
1 direct eval
35rank change if excluded
1 direct eval
61rank change if excluded
1 direct eval
Not shown0 direct evals-1.01 SDDirect
ministral-3-3b289rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals3rank change if excluded
1 direct eval
Not shown0 direct evals3rank change if excluded
1 direct eval
Not shown0 direct evals-1.20 SDDirect
gpt-4.5-previewNot shown0 direct evals20rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
10rank change if excluded
3 direct evals
4rank change if excluded
1 direct eval
9rank change if excluded
6 direct evals
20rank change if excluded
1 direct eval
+0.46 SDDirect
qwen2-72b-instructNot shown0 direct evals-2rank change if excluded
2 direct evals
-2rank change if excluded
1 direct eval
Not shown0 direct evals-4rank change if excluded
1 direct eval
-5rank change if excluded
9 direct evals
-2rank change if excluded
1 direct eval
-1.01 SDDirect
laguna-s-2.1-poolside-13rank change if excluded
2 direct evals
10rank change if excluded
2 direct evals
-10rank change if excluded
1 direct eval
-11rank change if excluded
2 direct evals
Not shown0 direct evals-11rank change if excluded
2 direct evals
-11rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
deepseek-v3.1100rank change if excluded
2 direct evals
-27rank change if excluded
1 direct eval
98rank change if excluded
2 direct evals
-39rank change if excluded
5 direct evals
96rank change if excluded
2 direct evals
-30rank change if excluded
8 direct evals
-27rank change if excluded
1 direct eval
-1.44 SDDirect
palmyra-x5Not shown0 direct evalsNot shown0 direct evals-18rank change if excluded
1 direct eval
Not shown0 direct evals-13rank change if excluded
1 direct eval
-2rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
o3Not shown0 direct evals17rank change if excluded
2 direct evals
-32rank change if excluded
4 direct evals
14rank change if excluded
8 direct evals
-33rank change if excluded
4 direct evals
18rank change if excluded
15 direct evals
-7rank change if excluded
6 direct evals
+1.05 SDDirect
minimax-m2.7-15rank change if excluded
2 direct evals
15rank change if excluded
6 direct evals
-10rank change if excluded
1 direct eval
-11rank change if excluded
9 direct evals
-14rank change if excluded
3 direct evals
-13rank change if excluded
6 direct evals
1rank change if excluded
5 direct evals
-0.09 SDMedian-imputed
kimi-k2-2rank change if excluded
1 direct eval
-20rank change if excluded
4 direct evals
0rank change if excluded
3 direct evals
-26rank change if excluded
13 direct evals
6rank change if excluded
2 direct evals
-19rank change if excluded
17 direct evals
1rank change if excluded
7 direct evals
-0.09 SDMedian-imputed
qwen-72b-chatNot shown0 direct evals50rank change if excluded
2 direct evals
49rank change if excluded
2 direct evals
49rank change if excluded
1 direct eval
Not shown0 direct evals139rank change if excluded
4 direct evals
Not shown0 direct evals-1.01 SDDirect
deepseek-v4-flash35rank change if excluded
4 direct evals
-12rank change if excluded
4 direct evals
0rank change if excluded
1 direct eval
-8rank change if excluded
9 direct evals
-7rank change if excluded
3 direct evals
-7rank change if excluded
6 direct evals
-8rank change if excluded
5 direct evals
-1.05 SDDirect
seed-2.0-mini24rank change if excluded
1 direct eval
-71rank change if excluded
2 direct evals
-40rank change if excluded
1 direct eval
-40rank change if excluded
2 direct evals
Not shown0 direct evals-40rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
gpt-oss-120b-16rank change if excluded
3 direct evals
10rank change if excluded
6 direct evals
8rank change if excluded
6 direct evals
-28rank change if excluded
12 direct evals
-15rank change if excluded
3 direct evals
10rank change if excluded
18 direct evals
-7rank change if excluded
5 direct evals
+1.05 SDDirect
mimo-v2.5-2rank change if excluded
2 direct evals
126rank change if excluded
1 direct eval
Not shown0 direct evals-8rank change if excluded
5 direct evals
-9rank change if excluded
2 direct evals
-4rank change if excluded
2 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
o1-mini42rank change if excluded
1 direct eval
42rank change if excluded
2 direct evals
62rank change if excluded
2 direct evals
-15rank change if excluded
2 direct evals
6rank change if excluded
1 direct eval
-153rank change if excluded
8 direct evals
6rank change if excluded
1 direct eval
+0.46 SDDirect
gemini-1.5-flash48rank change if excluded
2 direct evals
29rank change if excluded
2 direct evals
29rank change if excluded
2 direct evals
29rank change if excluded
1 direct eval
26rank change if excluded
3 direct evals
29rank change if excluded
13 direct evals
28rank change if excluded
4 direct evals
+0.76 SDDirect
hy3-30rank change if excluded
2 direct evals
-14rank change if excluded
2 direct evals
Not shown0 direct evals161rank change if excluded
3 direct evals
Not shown0 direct evals-8rank change if excluded
1 direct eval
-14rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
gpt-5.3-codexNot shown0 direct evals165rank change if excluded
2 direct evals
Not shown0 direct evals-12rank change if excluded
4 direct evals
-15rank change if excluded
1 direct eval
-11rank change if excluded
1 direct eval
2rank change if excluded
1 direct eval
+1.55 SDDirect
glm-5.27rank change if excluded
3 direct evals
2rank change if excluded
4 direct evals
6rank change if excluded
2 direct evals
2rank change if excluded
13 direct evals
6rank change if excluded
2 direct evals
5rank change if excluded
8 direct evals
2rank change if excluded
6 direct evals
-0.61 SDDirect
gpt-oss-safeguard-20b-87rank change if excluded
1 direct eval
-136rank change if excluded
2 direct evals
Not shown0 direct evals-136rank change if excluded
1 direct eval
Not shown0 direct evals47rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
+1.55 SDDirect
deepseek-v3.2-exp-118rank change if excluded
1 direct eval
-11rank change if excluded
1 direct eval
Not shown0 direct evals8rank change if excluded
2 direct evals
Not shown0 direct evals-11rank change if excluded
3 direct evals
26rank change if excluded
2 direct evals
-1.01 SDDirect
gpt-5.2-codexNot shown0 direct evals3rank change if excluded
1 direct eval
Not shown0 direct evals-8rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals3rank change if excluded
1 direct eval
+1.55 SDDirect
internlm-chat-20bNot shown0 direct evals7rank change if excluded
4 direct evals
-9rank change if excluded
4 direct evals
-9rank change if excluded
1 direct eval
Not shown0 direct evals7rank change if excluded
4 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
gemini-2.5-pro-9rank change if excluded
1 direct eval
-12rank change if excluded
9 direct evals
-12rank change if excluded
6 direct evals
38rank change if excluded
19 direct evals
37rank change if excluded
6 direct evals
37rank change if excluded
22 direct evals
-13rank change if excluded
11 direct evals
+0.60 SDDirect
gemini-3-pro-preview-18rank change if excluded
1 direct eval
-13rank change if excluded
2 direct evals
4rank change if excluded
2 direct evals
-13rank change if excluded
12 direct evals
1rank change if excluded
3 direct evals
-6rank change if excluded
14 direct evals
1rank change if excluded
6 direct evals
+0.97 SDDirect
qwen3.6-27bNot shown0 direct evals-14rank change if excluded
1 direct eval
Not shown0 direct evals-16rank change if excluded
1 direct eval
-14rank change if excluded
1 direct eval
-14rank change if excluded
1 direct eval
-122rank change if excluded
2 direct evals
-0.67 SDDirect
gemini-3.5-flash-lite-99rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals55rank change if excluded
5 direct evals
106rank change if excluded
3 direct evals
-66rank change if excluded
2 direct evals
-61rank change if excluded
1 direct eval
+1.16 SDDirect
internlm2-chat-20bNot shown0 direct evals-63rank change if excluded
2 direct evals
-2rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
Not shown0 direct evals-4rank change if excluded
5 direct evals
16rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
minimax-m2-13rank change if excluded
1 direct eval
4rank change if excluded
3 direct evals
-5rank change if excluded
1 direct eval
-3rank change if excluded
4 direct evals
Not shown0 direct evals3rank change if excluded
4 direct evals
-4rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
qwen2.5-72b-instruct180rank change if excluded
1 direct eval
-10rank change if excluded
1 direct eval
-11rank change if excluded
3 direct evals
-12rank change if excluded
4 direct evals
8rank change if excluded
3 direct evals
-10rank change if excluded
12 direct evals
-10rank change if excluded
2 direct evals
-1.01 SDDirect
grok-4.3-7rank change if excluded
2 direct evals
-12rank change if excluded
5 direct evals
-9rank change if excluded
3 direct evals
-10rank change if excluded
12 direct evals
-9rank change if excluded
2 direct evals
-10rank change if excluded
9 direct evals
-10rank change if excluded
7 direct evals
-0.62 SDDirect
longcat-2.0Not shown0 direct evals55rank change if excluded
1 direct eval
-8rank change if excluded
1 direct eval
-8rank change if excluded
3 direct evals
-8rank change if excluded
1 direct eval
-8rank change if excluded
2 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen3-235b-a22b21rank change if excluded
3 direct evals
26rank change if excluded
7 direct evals
30rank change if excluded
4 direct evals
22rank change if excluded
8 direct evals
25rank change if excluded
4 direct evals
24rank change if excluded
18 direct evals
8rank change if excluded
8 direct evals
-1.01 SDDirect
deepseek-v3.27rank change if excluded
4 direct evals
-29rank change if excluded
11 direct evals
-5rank change if excluded
3 direct evals
-20rank change if excluded
16 direct evals
-20rank change if excluded
2 direct evals
-20rank change if excluded
12 direct evals
-4rank change if excluded
9 direct evals
-1.01 SDDirect
gpt-4.1-mini6rank change if excluded
1 direct eval
2rank change if excluded
2 direct evals
1rank change if excluded
3 direct evals
6rank change if excluded
4 direct evals
7rank change if excluded
4 direct evals
12rank change if excluded
16 direct evals
-19rank change if excluded
3 direct evals
+1.05 SDDirect
olmo-3-7b-instructNot shown0 direct evals82rank change if excluded
1 direct eval
-3rank change if excluded
1 direct eval
-5rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-0.09 SDMedian-imputed
claude-haiku-5.5-216rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals33rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals33rank change if excluded
1 direct eval
+2.03 SDDirect
qwen3-30b-a3b216rank change if excluded
1 direct eval
-42rank change if excluded
1 direct eval
Not shown0 direct evals-40rank change if excluded
2 direct evals
Not shown0 direct evals-42rank change if excluded
3 direct evals
-42rank change if excluded
1 direct eval
-1.01 SDDirect
nemotron-3-nano-omni-30b-a3b259rank change if excluded
1 direct eval
Not shown0 direct evals5rank change if excluded
1 direct eval
0rank change if excluded
2 direct evals
Not shown0 direct evals6rank change if excluded
1 direct eval
5rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
grok-3-mini19rank change if excluded
1 direct eval
-54rank change if excluded
2 direct evals
24rank change if excluded
3 direct evals
24rank change if excluded
4 direct evals
25rank change if excluded
1 direct eval
25rank change if excluded
11 direct evals
-38rank change if excluded
2 direct evals
-0.07 SDDirect
phi-4-reasoning-plusNot shown0 direct evals10rank change if excluded
1 direct eval
9rank change if excluded
1 direct eval
Not shown0 direct evals9rank change if excluded
1 direct eval
10rank change if excluded
2 direct evals
10rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
doubao-seed-1.6Not shown0 direct evals-9rank change if excluded
4 direct evals
-2rank change if excluded
3 direct evals
-7rank change if excluded
4 direct evals
-6rank change if excluded
1 direct eval
-21rank change if excluded
5 direct evals
-2rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
grok-4-fast-3rank change if excluded
1 direct eval
Not shown0 direct evals31rank change if excluded
2 direct evals
-60rank change if excluded
8 direct evals
-2rank change if excluded
1 direct eval
-2rank change if excluded
7 direct evals
-2rank change if excluded
2 direct evals
-0.33 SDDirect
ernie-4.5-300b-a47bNot shown0 direct evals7rank change if excluded
1 direct eval
-5rank change if excluded
1 direct eval
-137rank change if excluded
3 direct evals
9rank change if excluded
1 direct eval
-4rank change if excluded
2 direct evals
-9rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
nova-2.0-liteNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals12rank change if excluded
3 direct evals
Not shown0 direct evals-4rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
claude-3-opus43rank change if excluded
5 direct evals
17rank change if excluded
4 direct evals
12rank change if excluded
4 direct evals
18rank change if excluded
5 direct evals
15rank change if excluded
4 direct evals
18rank change if excluded
15 direct evals
16rank change if excluded
7 direct evals
+2.01 SDDirect
kimi-k2.7-codeNot shown0 direct evals211rank change if excluded
3 direct evals
Not shown0 direct evals-21rank change if excluded
3 direct evals
Not shown0 direct evals-22rank change if excluded
1 direct eval
-21rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
qwen3-32b292rank change if excluded
1 direct eval
0rank change if excluded
1 direct eval
21rank change if excluded
1 direct eval
0rank change if excluded
2 direct evals
21rank change if excluded
1 direct eval
-1rank change if excluded
6 direct evals
0rank change if excluded
1 direct eval
-1.01 SDDirect
claude-3.5-sonnet-78rank change if excluded
4 direct evals
-8rank change if excluded
4 direct evals
-9rank change if excluded
3 direct evals
-9rank change if excluded
9 direct evals
-10rank change if excluded
4 direct evals
3rank change if excluded
19 direct evals
9rank change if excluded
8 direct evals
+2.01 SDDirect
glm-5.1-16rank change if excluded
2 direct evals
-22rank change if excluded
4 direct evals
-10rank change if excluded
1 direct eval
-15rank change if excluded
9 direct evals
-8rank change if excluded
1 direct eval
-12rank change if excluded
4 direct evals
-22rank change if excluded
8 direct evals
-0.61 SDDirect
ox-alpha-221rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals19rank change if excluded
3 direct evals
19rank change if excluded
1 direct eval
21rank change if excluded
1 direct eval
21rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
minimax-m2.5-12rank change if excluded
1 direct eval
-1rank change if excluded
3 direct evals
46rank change if excluded
2 direct evals
-23rank change if excluded
8 direct evals
-10rank change if excluded
1 direct eval
-9rank change if excluded
3 direct evals
-26rank change if excluded
3 direct evals
-0.09 SDMedian-imputed
olmo-3.1-32b-instructNot shown0 direct evals186rank change if excluded
1 direct eval
Not shown0 direct evals-7rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-0.09 SDMedian-imputed
gpt-4-turbo8rank change if excluded
1 direct eval
-8rank change if excluded
6 direct evals
-1rank change if excluded
4 direct evals
7rank change if excluded
5 direct evals
0rank change if excluded
3 direct evals
2rank change if excluded
19 direct evals
4rank change if excluded
7 direct evals
+0.46 SDDirect
deepseek-v3-27rank change if excluded
4 direct evals
4rank change if excluded
4 direct evals
7rank change if excluded
7 direct evals
3rank change if excluded
10 direct evals
3rank change if excluded
2 direct evals
6rank change if excluded
16 direct evals
9rank change if excluded
6 direct evals
-1.44 SDDirect
phi-3-mini-4k-instructNot shown0 direct evals2rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-1rank change if excluded
4 direct evals
3rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gemma-4-e4bNot shown0 direct evals-114rank change if excluded
1 direct eval
Not shown0 direct evals222rank change if excluded
1 direct eval
Not shown0 direct evals-114rank change if excluded
2 direct evals
-8rank change if excluded
1 direct eval
+1.16 SDDirect
qwen3.8-max-109rank change if excluded
2 direct evals
76rank change if excluded
2 direct evals
Not shown0 direct evals78rank change if excluded
5 direct evals
-104rank change if excluded
2 direct evals
-104rank change if excluded
3 direct evals
72rank change if excluded
3 direct evals
-0.67 SDDirect
grok-4.20-1rank change if excluded
1 direct eval
-16rank change if excluded
6 direct evals
3rank change if excluded
3 direct evals
5rank change if excluded
14 direct evals
1rank change if excluded
5 direct evals
0rank change if excluded
10 direct evals
-8rank change if excluded
7 direct evals
-0.62 SDDirect
phi-4Not shown0 direct evals0rank change if excluded
2 direct evals
-19rank change if excluded
1 direct eval
-212rank change if excluded
4 direct evals
Not shown0 direct evals-15rank change if excluded
3 direct evals
-19rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
mercury-2Not shown0 direct evals294rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
-37rank change if excluded
4 direct evals
Not shown0 direct evals1rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gemini-2.5-flash-9rank change if excluded
2 direct evals
-5rank change if excluded
6 direct evals
0rank change if excluded
4 direct evals
-8rank change if excluded
13 direct evals
-8rank change if excluded
4 direct evals
-14rank change if excluded
20 direct evals
-4rank change if excluded
10 direct evals
+0.60 SDDirect
qwen2.5-32b-instructNot shown0 direct evals12rank change if excluded
1 direct eval
Not shown0 direct evals-44rank change if excluded
2 direct evals
16rank change if excluded
1 direct eval
12rank change if excluded
2 direct evals
38rank change if excluded
2 direct evals
-1.01 SDDirect
grok-4-11rank change if excluded
1 direct eval
-7rank change if excluded
5 direct evals
16rank change if excluded
7 direct evals
14rank change if excluded
13 direct evals
-7rank change if excluded
2 direct evals
-6rank change if excluded
16 direct evals
-8rank change if excluded
5 direct evals
-0.07 SDDirect
qwen3.6-plus21rank change if excluded
1 direct eval
-2rank change if excluded
4 direct evals
12rank change if excluded
1 direct eval
4rank change if excluded
6 direct evals
12rank change if excluded
1 direct eval
19rank change if excluded
3 direct evals
-6rank change if excluded
2 direct evals
-0.67 SDDirect
granite-4.0-small-guardianNot shown0 direct evalsNot shown0 direct evals-70rank change if excluded
1 direct eval
Not shown0 direct evals-3rank change if excluded
1 direct eval
12rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen-14b-chatNot shown0 direct evals117rank change if excluded
5 direct evals
-36rank change if excluded
5 direct evals
40rank change if excluded
1 direct eval
Not shown0 direct evals40rank change if excluded
8 direct evals
Not shown0 direct evals-1.01 SDDirect
qwen3-next-80b-a3bNot shown0 direct evals-9rank change if excluded
1 direct eval
-22rank change if excluded
1 direct eval
-18rank change if excluded
3 direct evals
37rank change if excluded
2 direct evals
53rank change if excluded
9 direct evals
-9rank change if excluded
1 direct eval
-1.01 SDDirect
gpt-4o5rank change if excluded
3 direct evals
3rank change if excluded
12 direct evals
0rank change if excluded
9 direct evals
1rank change if excluded
21 direct evals
4rank change if excluded
6 direct evals
0rank change if excluded
37 direct evals
1rank change if excluded
20 direct evals
+0.46 SDDirect
deepseek-v4-pro193rank change if excluded
3 direct evals
-20rank change if excluded
4 direct evals
-12rank change if excluded
2 direct evals
-16rank change if excluded
12 direct evals
-19rank change if excluded
2 direct evals
-18rank change if excluded
7 direct evals
-18rank change if excluded
7 direct evals
-1.05 SDDirect
qwen3.6-max-previewNot shown0 direct evals-13rank change if excluded
1 direct eval
Not shown0 direct evals-16rank change if excluded
3 direct evals
Not shown0 direct evalsNot shown0 direct evals3rank change if excluded
2 direct evals
-0.67 SDDirect
space-bunny-alpha-112rank change if excluded
1 direct eval
-91rank change if excluded
1 direct eval
-92rank change if excluded
1 direct eval
-92rank change if excluded
1 direct eval
Not shown0 direct evals-92rank change if excluded
1 direct eval
83rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
qwen3-max-previewNot shown0 direct evalsNot shown0 direct evals250rank change if excluded
1 direct eval
-51rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-1.01 SDDirect
qwen3.7-plus-4rank change if excluded
1 direct eval
-3rank change if excluded
2 direct evals
-9rank change if excluded
1 direct eval
-15rank change if excluded
5 direct evals
Not shown0 direct evals-10rank change if excluded
2 direct evals
Not shown0 direct evals-0.67 SDDirect
gemini-2.0-pro-previewNot shown0 direct evalsNot shown0 direct evals76rank change if excluded
1 direct eval
Not shown0 direct evals-14rank change if excluded
1 direct eval
-25rank change if excluded
5 direct evals
Not shown0 direct evals+0.76 SDDirect
kimi-k2.5-2rank change if excluded
2 direct evals
20rank change if excluded
7 direct evals
-16rank change if excluded
4 direct evals
20rank change if excluded
15 direct evals
-8rank change if excluded
3 direct evals
-4rank change if excluded
13 direct evals
-8rank change if excluded
10 direct evals
-0.09 SDMedian-imputed
grok-4.6-166rank change if excluded
2 direct evals
14rank change if excluded
1 direct eval
Not shown0 direct evals13rank change if excluded
7 direct evals
14rank change if excluded
2 direct evals
14rank change if excluded
3 direct evals
11rank change if excluded
6 direct evals
-0.62 SDDirect
gpt-473rank change if excluded
1 direct eval
75rank change if excluded
6 direct evals
74rank change if excluded
6 direct evals
-29rank change if excluded
2 direct evals
-30rank change if excluded
2 direct evals
-31rank change if excluded
14 direct evals
-30rank change if excluded
1 direct eval
+0.46 SDDirect
mistral-mediumNot shown0 direct evals-4rank change if excluded
1 direct eval
Not shown0 direct evals43rank change if excluded
1 direct eval
46rank change if excluded
1 direct eval
43rank change if excluded
2 direct evals
-4rank change if excluded
1 direct eval
-1.20 SDDirect
qwen3.8-27b-262rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-6rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals-12rank change if excluded
1 direct eval
-0.67 SDDirect
grok-3-37rank change if excluded
2 direct evals
-6rank change if excluded
2 direct evals
-6rank change if excluded
3 direct evals
-5rank change if excluded
5 direct evals
-6rank change if excluded
1 direct eval
-5rank change if excluded
11 direct evals
-4rank change if excluded
2 direct evals
-0.07 SDDirect
qwen1.5-32b-chatNot shown0 direct evals30rank change if excluded
1 direct eval
30rank change if excluded
1 direct eval
31rank change if excluded
2 direct evals
-63rank change if excluded
1 direct eval
31rank change if excluded
4 direct evals
30rank change if excluded
1 direct eval
-1.01 SDDirect
nemotron-3-ultra-550b-a55b-18rank change if excluded
2 direct evals
-12rank change if excluded
2 direct evals
-14rank change if excluded
1 direct eval
-16rank change if excluded
6 direct evals
-111rank change if excluded
1 direct eval
-14rank change if excluded
3 direct evals
-15rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
glm-4.7-flash253rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals-33rank change if excluded
3 direct evals
Not shown0 direct evals-30rank change if excluded
1 direct eval
Not shown0 direct evals-0.59 SDDirect
nemotron-3-super-120b-a12b-20rank change if excluded
1 direct eval
7rank change if excluded
2 direct evals
Not shown0 direct evals-4rank change if excluded
5 direct evals
-138rank change if excluded
3 direct evals
-3rank change if excluded
5 direct evals
-16rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
qwen3-235b-a22b-instructNot shown0 direct evals181rank change if excluded
1 direct eval
Not shown0 direct evals-44rank change if excluded
2 direct evals
Not shown0 direct evals-11rank change if excluded
1 direct eval
-10rank change if excluded
1 direct eval
-1.01 SDDirect
claude-3-haiku9rank change if excluded
1 direct eval
9rank change if excluded
2 direct evals
8rank change if excluded
3 direct evals
-67rank change if excluded
4 direct evals
-43rank change if excluded
4 direct evals
9rank change if excluded
12 direct evals
3rank change if excluded
3 direct evals
+2.01 SDDirect
o3-miniNot shown0 direct evals5rank change if excluded
2 direct evals
6rank change if excluded
3 direct evals
6rank change if excluded
7 direct evals
4rank change if excluded
3 direct evals
17rank change if excluded
15 direct evals
5rank change if excluded
5 direct evals
+0.46 SDDirect
nova-premier-112rank change if excluded
1 direct eval
22rank change if excluded
1 direct eval
Not shown0 direct evals15rank change if excluded
1 direct eval
Not shown0 direct evals22rank change if excluded
2 direct evals
15rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
baichuan-2-13b-chatNot shown0 direct evals39rank change if excluded
6 direct evals
16rank change if excluded
6 direct evals
16rank change if excluded
2 direct evals
Not shown0 direct evals18rank change if excluded
13 direct evals
14rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
qwen3.5-flash-117rank change if excluded
1 direct eval
38rank change if excluded
1 direct eval
-139rank change if excluded
2 direct evals
37rank change if excluded
3 direct evals
Not shown0 direct evals-4rank change if excluded
2 direct evals
Not shown0 direct evals-0.67 SDDirect
nova-micro-221rank change if excluded
1 direct eval
1rank change if excluded
1 direct eval
Not shown0 direct evals4rank change if excluded
2 direct evals
Not shown0 direct evals1rank change if excluded
3 direct evals
1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
nemotron-3-nano-30b-a3b149rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-122rank change if excluded
5 direct evals
-123rank change if excluded
1 direct eval
-101rank change if excluded
3 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
gpt-3.5-turbo5rank change if excluded
2 direct evals
8rank change if excluded
7 direct evals
21rank change if excluded
10 direct evals
9rank change if excluded
4 direct evals
2rank change if excluded
3 direct evals
3rank change if excluded
20 direct evals
7rank change if excluded
3 direct evals
+0.46 SDDirect
qwen1.5-14b-chatNot shown0 direct evals26rank change if excluded
3 direct evals
26rank change if excluded
2 direct evals
25rank change if excluded
3 direct evals
Not shown0 direct evals26rank change if excluded
6 direct evals
25rank change if excluded
2 direct evals
-1.01 SDDirect
command-r-plus10rank change if excluded
1 direct eval
-12rank change if excluded
2 direct evals
-13rank change if excluded
2 direct evals
-11rank change if excluded
2 direct evals
-12rank change if excluded
1 direct eval
-12rank change if excluded
8 direct evals
49rank change if excluded
3 direct evals
-0.09 SDMedian-imputed
llama-3.3-70b-instruct108rank change if excluded
6 direct evals
1rank change if excluded
6 direct evals
2rank change if excluded
5 direct evals
3rank change if excluded
13 direct evals
1rank change if excluded
5 direct evals
1rank change if excluded
17 direct evals
2rank change if excluded
3 direct evals
-1.24 SDDirect
deepseek-v4-flash-0731-216rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals2rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals2rank change if excluded
1 direct eval
-1.05 SDDirect
text-davinci-003Not shown0 direct evals19rank change if excluded
2 direct evals
16rank change if excluded
2 direct evals
17rank change if excluded
1 direct eval
Not shown0 direct evals17rank change if excluded
3 direct evals
Not shown0 direct evals+0.46 SDDirect
qwen1.5-72b-chatNot shown0 direct evals14rank change if excluded
2 direct evals
4rank change if excluded
3 direct evals
13rank change if excluded
4 direct evals
18rank change if excluded
2 direct evals
16rank change if excluded
12 direct evals
19rank change if excluded
2 direct evals
-1.01 SDDirect
o4-miniNot shown0 direct evals-5rank change if excluded
3 direct evals
-7rank change if excluded
3 direct evals
-11rank change if excluded
12 direct evals
-11rank change if excluded
4 direct evals
-7rank change if excluded
17 direct evals
8rank change if excluded
7 direct evals
+1.05 SDDirect
deepseek-r15rank change if excluded
2 direct evals
-1rank change if excluded
9 direct evals
5rank change if excluded
11 direct evals
-3rank change if excluded
18 direct evals
0rank change if excluded
6 direct evals
-1rank change if excluded
26 direct evals
-1rank change if excluded
9 direct evals
-1.44 SDDirect
gemini-3.1-flash-lite-54rank change if excluded
3 direct evals
-6rank change if excluded
5 direct evals
-24rank change if excluded
5 direct evals
-5rank change if excluded
12 direct evals
-7rank change if excluded
5 direct evals
-8rank change if excluded
9 direct evals
-5rank change if excluded
5 direct evals
+1.16 SDDirect
llama-4-maverick-3rank change if excluded
2 direct evals
-3rank change if excluded
11 direct evals
-2rank change if excluded
5 direct evals
-2rank change if excluded
14 direct evals
0rank change if excluded
2 direct evals
-4rank change if excluded
22 direct evals
1rank change if excluded
6 direct evals
-0.43 SDDirect
gemini-2.0-flash-8rank change if excluded
1 direct eval
-6rank change if excluded
2 direct evals
1rank change if excluded
3 direct evals
-5rank change if excluded
8 direct evals
-5rank change if excluded
1 direct eval
19rank change if excluded
11 direct evals
-38rank change if excluded
3 direct evals
+0.76 SDDirect
glm-4-9b-chatNot shown0 direct evals34rank change if excluded
2 direct evals
29rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-37rank change if excluded
8 direct evals
29rank change if excluded
2 direct evals
-0.09 SDDirect
qwen3-30b-a3b-instruct-13rank change if excluded
1 direct eval
41rank change if excluded
2 direct evals
-15rank change if excluded
2 direct evals
-8rank change if excluded
2 direct evals
Not shown0 direct evals-8rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
-1.01 SDDirect
yi-34b-chatNot shown0 direct evals8rank change if excluded
4 direct evals
6rank change if excluded
4 direct evals
-1rank change if excluded
4 direct evals
Not shown0 direct evals10rank change if excluded
9 direct evals
9rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
granite-4.0-smallNot shown0 direct evalsNot shown0 direct evals-2rank change if excluded
1 direct eval
Not shown0 direct evals-3rank change if excluded
1 direct eval
9rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
solar-pro-4-162rank change if excluded
2 direct evals
15rank change if excluded
1 direct eval
12rank change if excluded
1 direct eval
13rank change if excluded
2 direct evals
Not shown0 direct evals12rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
llama-3.2-instruct-11b-visionNot shown0 direct evals-10rank change if excluded
1 direct eval
Not shown0 direct evals0rank change if excluded
1 direct eval
Not shown0 direct evals175rank change if excluded
2 direct evals
115rank change if excluded
1 direct eval
-1.24 SDDirect
hy3-preview138rank change if excluded
1 direct eval
-27rank change if excluded
2 direct evals
Not shown0 direct evals-16rank change if excluded
4 direct evals
Not shown0 direct evals-19rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gpt-5.4-nanoNot shown0 direct evals0rank change if excluded
1 direct eval
-200rank change if excluded
2 direct evals
6rank change if excluded
9 direct evals
-211rank change if excluded
2 direct evals
0rank change if excluded
4 direct evals
0rank change if excluded
4 direct evals
+1.60 SDDirect
gemma-2b-it-84rank change if excluded
1 direct eval
-133rank change if excluded
3 direct evals
-10rank change if excluded
2 direct evals
2rank change if excluded
1 direct eval
Not shown0 direct evals2rank change if excluded
4 direct evals
2rank change if excluded
1 direct eval
+0.76 SDDirect
llama-3.1-405b-instructNot shown0 direct evals-17rank change if excluded
3 direct evals
17rank change if excluded
3 direct evals
18rank change if excluded
7 direct evals
-3rank change if excluded
3 direct evals
14rank change if excluded
17 direct evals
56rank change if excluded
4 direct evals
-1.24 SDDirect
internlm-chat-7bNot shown0 direct evals-139rank change if excluded
5 direct evals
3rank change if excluded
5 direct evals
2rank change if excluded
1 direct eval
Not shown0 direct evals-139rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
mistral-small-3.1Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals0rank change if excluded
2 direct evals
Not shown0 direct evals45rank change if excluded
4 direct evals
Not shown0 direct evals-1.20 SDDirect
gpt-4.1-nanoNot shown0 direct evals-18rank change if excluded
1 direct eval
-61rank change if excluded
2 direct evals
-18rank change if excluded
3 direct evals
-17rank change if excluded
2 direct evals
99rank change if excluded
12 direct evals
-17rank change if excluded
1 direct eval
+1.05 SDDirect
deepseek-llm-7b-chatNot shown0 direct evals3rank change if excluded
1 direct eval
-19rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals41rank change if excluded
3 direct evals
Not shown0 direct evals-1.44 SDDirect
llama-2-13b-chatNot shown0 direct evals-1rank change if excluded
3 direct evals
0rank change if excluded
2 direct evals
0rank change if excluded
2 direct evals
-145rank change if excluded
1 direct eval
-1rank change if excluded
10 direct evals
-4rank change if excluded
2 direct evals
-1.24 SDDirect
qwen1.5-7b-chatNot shown0 direct evals16rank change if excluded
2 direct evals
16rank change if excluded
2 direct evals
15rank change if excluded
3 direct evals
30rank change if excluded
1 direct eval
15rank change if excluded
9 direct evals
24rank change if excluded
1 direct eval
-1.01 SDDirect
gemini-3-flash-preview-1rank change if excluded
2 direct evals
-10rank change if excluded
5 direct evals
-18rank change if excluded
3 direct evals
-9rank change if excluded
13 direct evals
-30rank change if excluded
3 direct evals
-3rank change if excluded
9 direct evals
-8rank change if excluded
6 direct evals
+0.97 SDDirect
gemma-7b-it-62rank change if excluded
1 direct eval
-63rank change if excluded
4 direct evals
-62rank change if excluded
2 direct evals
-4rank change if excluded
1 direct eval
61rank change if excluded
1 direct eval
5rank change if excluded
6 direct evals
-4rank change if excluded
1 direct eval
+0.76 SDDirect
step-3.5-flash-164rank change if excluded
1 direct eval
-13rank change if excluded
2 direct evals
-13rank change if excluded
1 direct eval
-27rank change if excluded
5 direct evals
Not shown0 direct evals-13rank change if excluded
1 direct eval
-13rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
granite-4.0-micro-guardianNot shown0 direct evalsNot shown0 direct evals-83rank change if excluded
1 direct eval
Not shown0 direct evals-23rank change if excluded
1 direct eval
92rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
grok-4.1-fast-81rank change if excluded
2 direct evals
-79rank change if excluded
7 direct evals
35rank change if excluded
3 direct evals
37rank change if excluded
12 direct evals
-76rank change if excluded
2 direct evals
62rank change if excluded
11 direct evals
32rank change if excluded
5 direct evals
-0.33 SDDirect
llama-2-7b-chat4rank change if excluded
1 direct eval
4rank change if excluded
4 direct evals
4rank change if excluded
5 direct evals
4rank change if excluded
2 direct evals
-75rank change if excluded
2 direct evals
5rank change if excluded
14 direct evals
6rank change if excluded
2 direct evals
-1.24 SDDirect
claude-2.1Not shown0 direct evalsNot shown0 direct evals-2rank change if excluded
1 direct eval
-2rank change if excluded
2 direct evals
-257rank change if excluded
2 direct evals
4rank change if excluded
5 direct evals
Not shown0 direct evals+2.01 SDDirect
qwen3-coder-480b-a35b-instructNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-19rank change if excluded
3 direct evals
Not shown0 direct evals-28rank change if excluded
1 direct eval
Not shown0 direct evals-1.01 SDDirect
gemini-2.0-flash-lite-119rank change if excluded
1 direct eval
6rank change if excluded
1 direct eval
3rank change if excluded
2 direct evals
3rank change if excluded
2 direct evals
Not shown0 direct evals17rank change if excluded
4 direct evals
Not shown0 direct evals+0.76 SDDirect
mistral-medium-3.5Not shown0 direct evals-118rank change if excluded
1 direct eval
104rank change if excluded
2 direct evals
-55rank change if excluded
5 direct evals
66rank change if excluded
1 direct eval
-91rank change if excluded
2 direct evals
Not shown0 direct evals-1.20 SDDirect
gemma-2-9b-it-4rank change if excluded
1 direct eval
-4rank change if excluded
3 direct evals
1rank change if excluded
4 direct evals
-2rank change if excluded
3 direct evals
2rank change if excluded
1 direct eval
-2rank change if excluded
6 direct evals
-2rank change if excluded
2 direct evals
+0.76 SDDirect
yi-6b-chatNot shown0 direct evals23rank change if excluded
3 direct evals
1rank change if excluded
3 direct evals
1rank change if excluded
3 direct evals
Not shown0 direct evals1rank change if excluded
5 direct evals
1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
llama-3.2-90b-vision-instructNot shown0 direct evals57rank change if excluded
1 direct eval
Not shown0 direct evals-48rank change if excluded
1 direct eval
Not shown0 direct evals57rank change if excluded
2 direct evals
-94rank change if excluded
2 direct evals
-1.24 SDDirect
glm-4.5-6rank change if excluded
1 direct eval
-2rank change if excluded
3 direct evals
-26rank change if excluded
2 direct evals
0rank change if excluded
6 direct evals
-5rank change if excluded
2 direct evals
-2rank change if excluded
4 direct evals
-3rank change if excluded
2 direct evals
-1.03 SDDirect
glm-4.75rank change if excluded
1 direct eval
-3rank change if excluded
1 direct eval
Not shown0 direct evals-10rank change if excluded
6 direct evals
-1rank change if excluded
1 direct eval
12rank change if excluded
4 direct evals
-1rank change if excluded
2 direct evals
-0.61 SDDirect
mistral-small-4-50rank change if excluded
1 direct eval
5rank change if excluded
2 direct evals
93rank change if excluded
2 direct evals
7rank change if excluded
5 direct evals
5rank change if excluded
1 direct eval
7rank change if excluded
2 direct evals
Not shown0 direct evals-1.20 SDDirect
claude-3-sonnet-12rank change if excluded
1 direct eval
-11rank change if excluded
2 direct evals
-11rank change if excluded
3 direct evals
-12rank change if excluded
2 direct evals
-6rank change if excluded
4 direct evals
-4rank change if excluded
11 direct evals
-17rank change if excluded
3 direct evals
+2.01 SDDirect
mimo-v2-flashNot shown0 direct evals-97rank change if excluded
3 direct evals
34rank change if excluded
1 direct eval
-65rank change if excluded
7 direct evals
31rank change if excluded
1 direct eval
-101rank change if excluded
3 direct evals
-66rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
step-3.7-flash67rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals0rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-0.09 SDMedian-imputed
glm-4.6-6rank change if excluded
1 direct eval
-3rank change if excluded
4 direct evals
34rank change if excluded
2 direct evals
89rank change if excluded
6 direct evals
Not shown0 direct evals-16rank change if excluded
5 direct evals
-2rank change if excluded
2 direct evals
-0.59 SDDirect
llama-3-70b-instruct5rank change if excluded
1 direct eval
5rank change if excluded
2 direct evals
5rank change if excluded
2 direct evals
-5rank change if excluded
1 direct eval
3rank change if excluded
2 direct evals
-10rank change if excluded
9 direct evals
-57rank change if excluded
2 direct evals
-1.24 SDDirect
llama-3-8b-instruct4rank change if excluded
1 direct eval
3rank change if excluded
4 direct evals
3rank change if excluded
2 direct evals
-5rank change if excluded
1 direct eval
-13rank change if excluded
2 direct evals
-3rank change if excluded
12 direct evals
-5rank change if excluded
1 direct eval
-1.24 SDDirect
gemini-2.5-flash-lite39rank change if excluded
3 direct evals
3rank change if excluded
2 direct evals
38rank change if excluded
2 direct evals
-2rank change if excluded
9 direct evals
-2rank change if excluded
1 direct eval
-68rank change if excluded
10 direct evals
3rank change if excluded
4 direct evals
+0.60 SDDirect
magistral-mediumNot shown0 direct evals0rank change if excluded
2 direct evals
-15rank change if excluded
2 direct evals
1rank change if excluded
4 direct evals
-8rank change if excluded
1 direct eval
-3rank change if excluded
6 direct evals
-1rank change if excluded
1 direct eval
-1.20 SDDirect
qwen3.5-4bNot shown0 direct evals23rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
44rank change if excluded
2 direct evals
23rank change if excluded
1 direct eval
Not shown0 direct evals-0.67 SDDirect
command-rNot shown0 direct evalsNot shown0 direct evals-16rank change if excluded
1 direct eval
Not shown0 direct evals-16rank change if excluded
1 direct eval
-16rank change if excluded
6 direct evals
150rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gemini-2.0-flash-lite-previewNot shown0 direct evals-22rank change if excluded
1 direct eval
9rank change if excluded
1 direct eval
Not shown0 direct evals-30rank change if excluded
1 direct eval
-22rank change if excluded
6 direct evals
-19rank change if excluded
1 direct eval
+0.76 SDDirect
mimo-v2.6-flash-223rank change if excluded
1 direct eval
-1rank change if excluded
2 direct evals
-4rank change if excluded
1 direct eval
-3rank change if excluded
3 direct evals
-2rank change if excluded
1 direct eval
-59rank change if excluded
3 direct evals
-4rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
deepseek-v3.1-terminusNot shown0 direct evals-12rank change if excluded
1 direct eval
Not shown0 direct evals-8rank change if excluded
2 direct evals
Not shown0 direct evals-11rank change if excluded
2 direct evals
9rank change if excluded
2 direct evals
-1.01 SDDirect
gemma-3-12bNot shown0 direct evals6rank change if excluded
2 direct evals
-4rank change if excluded
1 direct eval
3rank change if excluded
3 direct evals
3rank change if excluded
1 direct eval
53rank change if excluded
7 direct evals
3rank change if excluded
1 direct eval
+0.76 SDDirect
qwen3.5-122b-a10bNot shown0 direct evals10rank change if excluded
1 direct eval
Not shown0 direct evals-75rank change if excluded
3 direct evals
11rank change if excluded
1 direct eval
9rank change if excluded
1 direct eval
11rank change if excluded
2 direct evals
-0.67 SDDirect
gemma-2-27b-it-11rank change if excluded
1 direct eval
-10rank change if excluded
2 direct evals
-11rank change if excluded
1 direct eval
-11rank change if excluded
2 direct evals
42rank change if excluded
1 direct eval
-10rank change if excluded
3 direct evals
-11rank change if excluded
1 direct eval
+0.76 SDDirect
yi-1.5-9b-chatNot shown0 direct evals-1rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals1rank change if excluded
3 direct evals
-20rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
glm-5-turboNot shown0 direct evals-247rank change if excluded
3 direct evals
-21rank change if excluded
1 direct eval
11rank change if excluded
5 direct evals
-19rank change if excluded
1 direct eval
-21rank change if excluded
3 direct evals
-21rank change if excluded
3 direct evals
-0.61 SDDirect
olmo-2-32b-instructNot shown0 direct evals14rank change if excluded
1 direct eval
-15rank change if excluded
2 direct evals
16rank change if excluded
1 direct eval
-13rank change if excluded
1 direct eval
21rank change if excluded
6 direct evals
-3rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
llama-3.1-70b-instruct60rank change if excluded
1 direct eval
60rank change if excluded
3 direct evals
25rank change if excluded
3 direct evals
-12rank change if excluded
2 direct evals
-12rank change if excluded
4 direct evals
-19rank change if excluded
15 direct evals
-4rank change if excluded
4 direct evals
-1.24 SDDirect
chatglm-6bNot shown0 direct evals0rank change if excluded
2 direct evals
0rank change if excluded
3 direct evals
0rank change if excluded
1 direct eval
Not shown0 direct evals23rank change if excluded
4 direct evals
Not shown0 direct evals-0.09 SDDirect
qwen2.5-7b-instruct18rank change if excluded
1 direct eval
-1rank change if excluded
2 direct evals
-1rank change if excluded
4 direct evals
-2rank change if excluded
1 direct eval
0rank change if excluded
1 direct eval
-4rank change if excluded
15 direct evals
-7rank change if excluded
3 direct evals
-1.01 SDDirect
phi-3.5-mini-instruct-67rank change if excluded
1 direct eval
-67rank change if excluded
4 direct evals
-67rank change if excluded
2 direct evals
23rank change if excluded
1 direct eval
Not shown0 direct evals23rank change if excluded
4 direct evals
23rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
qwen-7b-chatNot shown0 direct evals23rank change if excluded
6 direct evals
-1rank change if excluded
6 direct evals
-1rank change if excluded
1 direct eval
Not shown0 direct evals-11rank change if excluded
9 direct evals
Not shown0 direct evals-1.01 SDDirect
ernie-5.1Not shown0 direct evals37rank change if excluded
1 direct eval
Not shown0 direct evals-81rank change if excluded
3 direct evals
Not shown0 direct evals26rank change if excluded
1 direct eval
26rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
baichuan-2-7b-chatNot shown0 direct evals-7rank change if excluded
5 direct evals
-9rank change if excluded
5 direct evals
-9rank change if excluded
2 direct evals
Not shown0 direct evals-29rank change if excluded
11 direct evals
-9rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
qwen3.5-35b-a3bNot shown0 direct evals138rank change if excluded
1 direct eval
Not shown0 direct evals-42rank change if excluded
3 direct evals
Not shown0 direct evals138rank change if excluded
1 direct eval
126rank change if excluded
2 direct evals
-0.67 SDDirect
mercury-2.5-152rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-9rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-11rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
phi-2Not shown0 direct evals130rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-40rank change if excluded
3 direct evals
-17rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
gpt-4o-mini13rank change if excluded
3 direct evals
13rank change if excluded
3 direct evals
13rank change if excluded
4 direct evals
9rank change if excluded
6 direct evals
9rank change if excluded
4 direct evals
12rank change if excluded
20 direct evals
0rank change if excluded
6 direct evals
+0.46 SDDirect
nvidia-nemotron-nano-9b-v2Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals6rank change if excluded
2 direct evals
Not shown0 direct evals-28rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
llama-2-70b-chatNot shown0 direct evals2rank change if excluded
2 direct evals
2rank change if excluded
1 direct eval
2rank change if excluded
2 direct evals
-193rank change if excluded
2 direct evals
2rank change if excluded
9 direct evals
2rank change if excluded
2 direct evals
-1.24 SDDirect
o3-proNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-1rank change if excluded
3 direct evals
-174rank change if excluded
1 direct eval
2rank change if excluded
1 direct eval
Not shown0 direct evals+1.05 SDDirect
yi-1.5-34b-chatNot shown0 direct evals-2rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
Not shown0 direct evals21rank change if excluded
4 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen2.5-14b-instructNot shown0 direct evals-5rank change if excluded
2 direct evals
-1rank change if excluded
2 direct evals
-3rank change if excluded
1 direct eval
Not shown0 direct evals0rank change if excluded
5 direct evals
-5rank change if excluded
2 direct evals
-1.01 SDDirect
gemma-3-27b-itNot shown0 direct evals1rank change if excluded
2 direct evals
13rank change if excluded
3 direct evals
-1rank change if excluded
8 direct evals
13rank change if excluded
1 direct eval
3rank change if excluded
7 direct evals
1rank change if excluded
1 direct eval
+0.76 SDDirect
chatglm3-6bNot shown0 direct evals-14rank change if excluded
6 direct evals
-32rank change if excluded
6 direct evals
10rank change if excluded
2 direct evals
Not shown0 direct evals-31rank change if excluded
10 direct evals
Not shown0 direct evals-0.09 SDDirect
nova-pro-72rank change if excluded
1 direct eval
14rank change if excluded
1 direct eval
Not shown0 direct evals2rank change if excluded
4 direct evals
14rank change if excluded
1 direct eval
14rank change if excluded
3 direct evals
14rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
vicuna-7b-v1.5-11rank change if excluded
1 direct eval
-11rank change if excluded
1 direct eval
-11rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-36rank change if excluded
3 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
mistral-medium-3.1-33rank change if excluded
1 direct eval
-31rank change if excluded
1 direct eval
-31rank change if excluded
1 direct eval
-78rank change if excluded
5 direct evals
40rank change if excluded
1 direct eval
83rank change if excluded
4 direct evals
92rank change if excluded
2 direct evals
-1.20 SDDirect
minimax-m2.1Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-175rank change if excluded
5 direct evals
3rank change if excluded
1 direct eval
2rank change if excluded
3 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
mistral-small-3Not shown0 direct evals-1rank change if excluded
1 direct eval
24rank change if excluded
1 direct eval
0rank change if excluded
2 direct evals
0rank change if excluded
1 direct eval
-27rank change if excluded
6 direct evals
0rank change if excluded
1 direct eval
-1.20 SDDirect
trinity-largeNot shown0 direct evals17rank change if excluded
1 direct eval
Not shown0 direct evals41rank change if excluded
7 direct evals
17rank change if excluded
1 direct eval
17rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
llama-4-scout6rank change if excluded
1 direct eval
-9rank change if excluded
4 direct evals
6rank change if excluded
4 direct evals
1rank change if excluded
6 direct evals
4rank change if excluded
1 direct eval
1rank change if excluded
13 direct evals
3rank change if excluded
2 direct evals
-0.43 SDDirect
mistral-7b-instruct13rank change if excluded
1 direct eval
6rank change if excluded
6 direct evals
14rank change if excluded
6 direct evals
0rank change if excluded
4 direct evals
26rank change if excluded
4 direct evals
-24rank change if excluded
19 direct evals
4rank change if excluded
2 direct evals
-1.20 SDDirect
mistral-small-3.2Not shown0 direct evals11rank change if excluded
1 direct eval
46rank change if excluded
1 direct eval
-52rank change if excluded
3 direct evals
Not shown0 direct evals4rank change if excluded
3 direct evals
11rank change if excluded
1 direct eval
-1.20 SDDirect
qwen3-vl-32b-instructNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-15rank change if excluded
1 direct eval
76rank change if excluded
1 direct eval
76rank change if excluded
2 direct evals
Not shown0 direct evals-1.01 SDDirect
gemma-2-2b-it-35rank change if excluded
1 direct eval
-35rank change if excluded
2 direct evals
-35rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals39rank change if excluded
3 direct evals
-4rank change if excluded
1 direct eval
+0.76 SDDirect
palmyra-medNot shown0 direct evalsNot shown0 direct evals-21rank change if excluded
1 direct eval
Not shown0 direct evals4rank change if excluded
1 direct eval
8rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
vicuna-13b-v1.5-36rank change if excluded
1 direct eval
-36rank change if excluded
1 direct eval
-36rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-1rank change if excluded
3 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen2-7b-instructNot shown0 direct evals13rank change if excluded
1 direct eval
13rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-43rank change if excluded
4 direct evals
13rank change if excluded
1 direct eval
-1.01 SDDirect
olmo-3.1-32b-thinkNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals2rank change if excluded
3 direct evals
Not shown0 direct evals0rank change if excluded
1 direct eval
Not shown0 direct evals-0.09 SDMedian-imputed
vicuna-13bNot shown0 direct evals41rank change if excluded
2 direct evals
16rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals15rank change if excluded
4 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
mistral-nemo82rank change if excluded
2 direct evals
82rank change if excluded
2 direct evals
82rank change if excluded
1 direct eval
-30rank change if excluded
1 direct eval
Not shown0 direct evals-33rank change if excluded
3 direct evals
Not shown0 direct evals-1.20 SDDirect
granite-3.3-8b-instructNot shown0 direct evalsNot shown0 direct evals-1rank change if excluded
1 direct eval
-79rank change if excluded
2 direct evals
0rank change if excluded
1 direct eval
0rank change if excluded
6 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen2.5-maxNot shown0 direct evals20rank change if excluded
1 direct eval
5rank change if excluded
1 direct eval
59rank change if excluded
3 direct evals
-41rank change if excluded
1 direct eval
20rank change if excluded
3 direct evals
20rank change if excluded
1 direct eval
-1.01 SDDirect
qwen2.5-1.5b-instructNot shown0 direct evals-18rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals0rank change if excluded
5 direct evals
-18rank change if excluded
1 direct eval
-1.01 SDDirect
qwen2.5-3b-instructNot shown0 direct evals-328rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-2rank change if excluded
3 direct evals
2rank change if excluded
1 direct eval
-1.01 SDDirect
muse-glimmer-21rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals32rank change if excluded
2 direct evals
-20rank change if excluded
1 direct eval
-21rank change if excluded
1 direct eval
Not shown0 direct evals+0.35 SDDirect
gemma-3-4bNot shown0 direct evals-6rank change if excluded
2 direct evals
35rank change if excluded
1 direct eval
-6rank change if excluded
1 direct eval
-6rank change if excluded
1 direct eval
-48rank change if excluded
4 direct evals
-6rank change if excluded
1 direct eval
+0.76 SDDirect
chatglm2-6bNot shown0 direct evals-23rank change if excluded
4 direct evals
-24rank change if excluded
4 direct evals
Not shown0 direct evalsNot shown0 direct evals-24rank change if excluded
6 direct evals
Not shown0 direct evals-0.09 SDDirect
qwen1.5-0.5b-chatNot shown0 direct evals-18rank change if excluded
1 direct eval
-8rank change if excluded
1 direct eval
-10rank change if excluded
1 direct eval
Not shown0 direct evals-8rank change if excluded
3 direct evals
Not shown0 direct evals-1.01 SDDirect
olmo-2-13b-instructNot shown0 direct evals12rank change if excluded
1 direct eval
-13rank change if excluded
2 direct evals
4rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
3rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
ling-2.6-flash-164rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-29rank change if excluded
2 direct evals
0rank change if excluded
1 direct eval
0rank change if excluded
1 direct eval
22rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
qwen3-14bNot shown0 direct evals-1rank change if excluded
2 direct evals
-31rank change if excluded
2 direct evals
1rank change if excluded
2 direct evals
-31rank change if excluded
1 direct eval
-1rank change if excluded
2 direct evals
-1rank change if excluded
1 direct eval
-1.01 SDDirect
llama-3.1-8b-instruct2rank change if excluded
1 direct eval
-30rank change if excluded
5 direct evals
-1rank change if excluded
7 direct evals
3rank change if excluded
6 direct evals
1rank change if excluded
4 direct evals
-30rank change if excluded
20 direct evals
13rank change if excluded
5 direct evals
-1.24 SDDirect
zephyr-7b-betaNot shown0 direct evals-1rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-157rank change if excluded
5 direct evals
-1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
seallms-v3-7b-chatNot shown0 direct evals-15rank change if excluded
1 direct eval
-45rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals1rank change if excluded
2 direct evals
8rank change if excluded
1 direct eval
-1.01 SDDirect
mixtral-8x22b-instructNot shown0 direct evals-17rank change if excluded
2 direct evals
47rank change if excluded
1 direct eval
Not shown0 direct evals-13rank change if excluded
2 direct evals
-75rank change if excluded
8 direct evals
45rank change if excluded
1 direct eval
-1.20 SDDirect
mistral-medium-3-9rank change if excluded
1 direct eval
-9rank change if excluded
1 direct eval
Not shown0 direct evals40rank change if excluded
4 direct evals
Not shown0 direct evals-9rank change if excluded
1 direct eval
-9rank change if excluded
2 direct evals
-1.20 SDDirect
qwen3-8bNot shown0 direct evals-2rank change if excluded
3 direct evals
3rank change if excluded
3 direct evals
-1rank change if excluded
2 direct evals
1rank change if excluded
2 direct evals
-3rank change if excluded
5 direct evals
-1rank change if excluded
2 direct evals
-1.01 SDDirect
mistral-7bNot shown0 direct evals2rank change if excluded
1 direct eval
Not shown0 direct evals-16rank change if excluded
2 direct evals
Not shown0 direct evals-92rank change if excluded
3 direct evals
4rank change if excluded
2 direct evals
-1.20 SDDirect
command-aNot shown0 direct evals16rank change if excluded
2 direct evals
14rank change if excluded
2 direct evals
-3rank change if excluded
6 direct evals
Not shown0 direct evals-4rank change if excluded
5 direct evals
-3rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
moss-moon-003-sftNot shown0 direct evals3rank change if excluded
2 direct evals
3rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals3rank change if excluded
3 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
phi-4-miniNot shown0 direct evals0rank change if excluded
1 direct eval
Not shown0 direct evals-7rank change if excluded
2 direct evals
Not shown0 direct evals0rank change if excluded
2 direct evals
0rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
qwen2.5-7bNot shown0 direct evalsNot shown0 direct evals-2rank change if excluded
2 direct evals
-2rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals-1.01 SDDirect
qwen3-next-80b-a3b-instructNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-205rank change if excluded
2 direct evals
Not shown0 direct evals3rank change if excluded
2 direct evals
Not shown0 direct evals-1.01 SDDirect
llama-3.2-1b-instruct23rank change if excluded
1 direct eval
23rank change if excluded
2 direct evals
23rank change if excluded
1 direct eval
-8rank change if excluded
1 direct eval
Not shown0 direct evals-60rank change if excluded
7 direct evals
-8rank change if excluded
1 direct eval
-1.24 SDDirect
vicuna-33b-v1.3Not shown0 direct evals5rank change if excluded
2 direct evals
5rank change if excluded
2 direct evals
-15rank change if excluded
1 direct eval
Not shown0 direct evals-1rank change if excluded
4 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
vicuna-7bNot shown0 direct evals12rank change if excluded
2 direct evals
-34rank change if excluded
2 direct evals
Not shown0 direct evalsNot shown0 direct evals-27rank change if excluded
5 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen3-vl-235b-a22b-instructNot shown0 direct evals2rank change if excluded
1 direct eval
Not shown0 direct evals-234rank change if excluded
2 direct evals
Not shown0 direct evals2rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
-1.01 SDDirect
davinciNot shown0 direct evals4rank change if excluded
1 direct eval
4rank change if excluded
1 direct eval
0rank change if excluded
2 direct evals
Not shown0 direct evals4rank change if excluded
2 direct evals
Not shown0 direct evals+0.46 SDDirect
granite-4.0-microNot shown0 direct evals1rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
-55rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
1rank change if excluded
6 direct evals
0rank change if excluded
2 direct evals
-0.09 SDMedian-imputed
deepseek-v3.2-specialeNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals9rank change if excluded
1 direct eval
Not shown0 direct evals-2rank change if excluded
1 direct eval
-6rank change if excluded
1 direct eval
-1.01 SDDirect
mistral-large-3Not shown0 direct evals-1rank change if excluded
5 direct evals
-1rank change if excluded
4 direct evals
-4rank change if excluded
11 direct evals
-1rank change if excluded
2 direct evals
3rank change if excluded
8 direct evals
-1rank change if excluded
1 direct eval
-1.20 SDDirect
grok-build-0.1Not shown0 direct evals10rank change if excluded
2 direct evals
Not shown0 direct evals-29rank change if excluded
2 direct evals
Not shown0 direct evals-9rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
-0.62 SDDirect
deepseek-llm-67b-chatNot shown0 direct evals-41rank change if excluded
1 direct eval
-54rank change if excluded
1 direct eval
Not shown0 direct evals-53rank change if excluded
1 direct eval
-11rank change if excluded
7 direct evals
-53rank change if excluded
1 direct eval
-1.44 SDDirect
qwen3-vl-8b-instructNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals0rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
-3rank change if excluded
2 direct evals
-2rank change if excluded
1 direct eval
-1.01 SDDirect
marin-8b-instructNot shown0 direct evalsNot shown0 direct evals0rank change if excluded
1 direct eval
Not shown0 direct evals0rank change if excluded
1 direct eval
0rank change if excluded
4 direct evals
Not shown0 direct evals-0.09 SDMedian-imputed
qwen3-4b-instructNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals4rank change if excluded
1 direct eval
Not shown0 direct evals1rank change if excluded
2 direct evals
Not shown0 direct evals-1.01 SDDirect
qwq-32bNot shown0 direct evals-104rank change if excluded
3 direct evals
7rank change if excluded
2 direct evals
6rank change if excluded
2 direct evals
Not shown0 direct evals-17rank change if excluded
3 direct evals
9rank change if excluded
1 direct eval
-1.01 SDDirect
mixtral-8x7b-instructNot shown0 direct evals-17rank change if excluded
2 direct evals
-18rank change if excluded
2 direct evals
-17rank change if excluded
2 direct evals
-17rank change if excluded
1 direct eval
-5rank change if excluded
12 direct evals
-17rank change if excluded
2 direct evals
-1.20 SDDirect
jamba-1.7-largeNot shown0 direct evals2rank change if excluded
1 direct eval
Not shown0 direct evals-3rank change if excluded
3 direct evals
Not shown0 direct evals-5rank change if excluded
1 direct eval
-5rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
olmo-2-7b-instructNot shown0 direct evals6rank change if excluded
1 direct eval
-2rank change if excluded
1 direct eval
Not shown0 direct evals-2rank change if excluded
1 direct eval
6rank change if excluded
5 direct evals
1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
mistral-large-2Not shown0 direct evals-12rank change if excluded
2 direct evals
2rank change if excluded
3 direct evals
3rank change if excluded
7 direct evals
Not shown0 direct evals2rank change if excluded
9 direct evals
2rank change if excluded
1 direct eval
-1.20 SDDirect
jamba-1.7-miniNot shown0 direct evals6rank change if excluded
1 direct eval
Not shown0 direct evals-4rank change if excluded
2 direct evals
Not shown0 direct evals-8rank change if excluded
1 direct eval
-9rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
qwen-1.8b-chatNot shown0 direct evals2rank change if excluded
1 direct eval
-3rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals2rank change if excluded
3 direct evals
Not shown0 direct evals-1.01 SDDirect
command-r7bNot shown0 direct evals1rank change if excluded
1 direct eval
Not shown0 direct evals-4rank change if excluded
1 direct eval
Not shown0 direct evals1rank change if excluded
3 direct evals
-4rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
dbrx-instructNot shown0 direct evals-9rank change if excluded
1 direct eval
0rank change if excluded
1 direct eval
Not shown0 direct evals-1rank change if excluded
1 direct eval
-13rank change if excluded
6 direct evals
-1rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
olmoe-1b-7b-instructNot shown0 direct evals-2rank change if excluded
1 direct eval
-3rank change if excluded
1 direct eval
Not shown0 direct evals-2rank change if excluded
1 direct eval
2rank change if excluded
5 direct evals
-2rank change if excluded
1 direct eval
-0.09 SDMedian-imputed
llama-3.2-3bNot shown0 direct evals-5rank change if excluded
1 direct eval
11rank change if excluded
1 direct eval
Not shown0 direct evals11rank change if excluded
2 direct evals
-5rank change if excluded
2 direct evals
Not shown0 direct evals-1.24 SDDirect
grok-2Not shown0 direct evalsNot shown0 direct evals3rank change if excluded
1 direct eval
3rank change if excluded
3 direct evals
Not shown0 direct evals-128rank change if excluded
2 direct evals
Not shown0 direct evals-1.24 SDDirect
deepseek-r1-distill-llama-70bNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals0rank change if excluded
2 direct evals
4rank change if excluded
1 direct eval
4rank change if excluded
2 direct evals
Not shown0 direct evals-1.44 SDDirect
qwen1.5-1.8b-chatNot shown0 direct evals3rank change if excluded
1 direct eval
3rank change if excluded
1 direct eval
3rank change if excluded
2 direct evals
Not shown0 direct evals3rank change if excluded
4 direct evals
3rank change if excluded
1 direct eval
-1.01 SDDirect
llama-3.2-3b-instruct1rank change if excluded
1 direct eval
1rank change if excluded
2 direct evals
1rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evals1rank change if excluded
6 direct evals
1rank change if excluded
2 direct evals
-1.24 SDDirect
magistral-smallNot shown0 direct evals2rank change if excluded
1 direct eval
2rank change if excluded
1 direct eval
22rank change if excluded
2 direct evals
Not shown0 direct evals-44rank change if excluded
4 direct evals
2rank change if excluded
1 direct eval
-1.20 SDDirect
qwen2.5-0.5b-instructNot shown0 direct evals-1rank change if excluded
1 direct eval
Not shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals0rank change if excluded
4 direct evals
-1rank change if excluded
1 direct eval
-1.01 SDDirect
llama-3.1-8b-baseNot shown0 direct evalsNot shown0 direct evals-13rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
-1rank change if excluded
1 direct eval
Not shown0 direct evals-1.24 SDDirect
ministral-3-14bNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals5rank change if excluded
2 direct evals
Not shown0 direct evals-10rank change if excluded
1 direct eval
Not shown0 direct evals-1.20 SDDirect
ministral-3-8bNot shown0 direct evalsNot shown0 direct evalsNot shown0 direct evals-1rank change if excluded
2 direct evals
Not shown0 direct evals0rank change if excluded
2 direct evals
Not shown0 direct evals-1.20 SDDirect