Model profile
Kimi K2
Moonshot AIdeveloper
2025-07-11release date
#78 / 309overall rank
30eval lineages
Evidence summary
Kimi K2 has an estimated overall rank of #78; its 90% source-sensitivity interval is #59–#180. Its behavior-only rank is #79; company governance moves the combined estimate to #78. Published evidence spans 30 evals and 7 of 7 behavior components. Its strongest relative result is HELM Safety (simple_safety_tests, #1 of 80); its weakest is LiveSecBench (factuality, #41 of 43).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗kimi-k2
- Hugging Face ↗moonshotai/Kimi-K2-Instruct
- OpenRouter ↗moonshotai/kimi-k2
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #114 / 328 | ↓0.7267 | Source ↗official | |
| AgentDrive Safety Compliancescr | #19 / 48 | ↑89.38 | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #28 / 80 | ↑0.741 | Source ↗official | |
| Alignment Leaderboardcorrigibility | #3 / 24 | ↑4.495 | Source ↗official | |
| Alignment Leaderboardhonesty | #7 / 24 | ↑3.765 | Source ↗official | |
| Alignment Leaderboardnon_manipulation | #8 / 24 | ↑3.598 | Source ↗official | |
| Alignment Leaderboardrobustness | #18 / 24 | ↑3.267 | Source ↗official | |
| Alignment Leaderboardsafety | #9 / 24 | ↑3.923 | Source ↗official | |
| Alignment Leaderboardscheming | #8 / 24 | ↑3.898 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #83 / 112 | ↑1420.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #86 / 106 | ↑0.1 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #41 / 44 | ↓92.8 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #42 / 49 | ↓93 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #35 / 50 | ↓67.8 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #13 / 46 | ↓84.2 | Source ↗official | |
| CAIS Risk Indexmask | #33 / 52 | ↓30.7 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #9 / 49 | ↓14.6 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #35 / 104 | ↓20.59 | Source ↗official | |
| Confabulationsconfabulation_rate | #37 / 52 | ↓30.2 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #48 / 241 | ↑28.81 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #191 / 241 | ↑81.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #88 / 241 | ↑79.16 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #195 / 239 | ↑90.97 | Source ↗official | |
| FORTRESSaverage_risk_score | #40 / 49 | ↓55.47 | Source ↗official | |
| HELM Safetyanthropic_red_team | #27 / 80 | ↑0.993 | Source ↗official | |
| HELM Safetybbq | #28 / 80 | ↑0.949 | Source ↗official | |
| HELM Safetyharmbench | #8 / 80 | ↑0.974 | Source ↗official | |
| HELM Safetysimple_safety_tests | #1 / 80 | ↑1 | Source ↗official | |
| HELM Safetyxstest | #9 / 80 | ↑0.982 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #48 / 54 | ↑23.64 | Source ↗official | |
| LiveSecBenchethics | #40 / 43 | ↑20.12 | Source ↗official | |
| LiveSecBenchfactuality | #41 / 43 | ↑18.45 | Source ↗official | |
| LiveSecBenchlegality | #27 / 43 | ↑31.19 | Source ↗official | |
| LiveSecBenchprivacy | #8 / 43 | ↑73.81 | Source ↗official | |
| LiveSecBenchpsychological_health | #30 / 43 | ↑34.35 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #13 / 50 | ↓84.2 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #17 / 31 | ↓8.667 | Source ↗self run | |
| MASKlying_probability_pct | #47 / 53 | ↓53.33 | Source ↗official | |
| RealityTest — Text AI-Identity Disclosuredisclosure_probability | #4 / 17 | ↑0.552 | Source ↗official | |
| Shelleducation_jsr | #4 / 14 | ↓0.426 | Source ↗official | |
| Shellfinance_jsr | #3 / 14 | ↓0.22 | Source ↗official | |
| Shellmanagement_jsr | #2 / 14 | ↓0.346 | Source ↗official | |
| Social Welfare Function Benchmarkfairness | #1 / 19 | ↑0.637 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #66 / 113 | ↑6.725 | Source ↗official | |
| SpeciEvalland_animal_4ns | #83 / 113 | ↓4.775 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #102 / 113 | ↓5.13 | Source ↗official | |
| SpeciEvalspeciesism | #19 / 113 | ↓1.505 | Source ↗official | |
| UAVBench safety-critical decision recognitionethical_safety_critical_accuracy | #15 / 27 | ↑0.685 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #86 / 94 | ↑82.1 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.