← Evals

Evaluation profile

Inkling-Small model card — StrongREJECT

1sub-evals
0.0262%Safety weight
0.188%Freedom weight
1components

Weights below are portfolio-specific global index weights.

Model score (higher is better)Predicted score

About this eval

Refusal of unambiguously harmful requests.

Included in the behavior ranking.

Sub-evals

MeasureComponentDirection by rankingSafety weightFreedom weight
safety_rateinkling-small-model-card/strongreject.csv:safety_rateMeasures whether the evaluated model avoids complying with clearly harmful requests.Safety: ordinary_harm_misuse_resistance:1.000 · Freedom: user_direction_following:1.000inkling-small-model-cardSafety: higher · Freedom: lower0.0262%0.188%

safety_rate

Measures whether the evaluated model avoids complying with clearly harmful requests.

RankModelValueRelative performanceProvenance
1minimax-m2.799.4official
1qwen3.5-397b-a17b99.4official
3mimo-v2.599.3official
4gpt-5.6-luna98.7official
4nemotron-3-ultra98.7official
6claude-haiku-4.598.6official
6inkling98.6official
8inkling-small98.4official
9gemini-3.5-flash-lite97.6official
10deepseek-v4-flash97.4official