Model profile
Kimi K2.7 Code
Evidence summary
Safety. Kimi K2.7 Code has an estimated Safety rank of #148; its 90% source-sensitivity interval is #73–#278. Its behavior-only rank is #149; company governance moves the combined estimate to #148. Published Safety evidence spans 4 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #26 of 272); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #249 of 272).
Freedom. Kimi K2.7 Code has an estimated Freedom rank of #473; its 90% source-sensitivity interval is #306–#579. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #24 of 272); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #241 of 272).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗kimi-k2-7-code
- Hugging Face ↗moonshotai/Kimi-K2.7-Code
- OpenRouter ↗moonshotai/kimi-k2.7-code
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
Blackfrost-AI/KIMI-2.7-CODE-BF16-DERISKED ↗Direct non-quantized finetune documented by Hugging Face metadata
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #207 / 361 | ↓0.8238 | Source ↗official | |
| DystopiaBenchbasaglia_score | #16 / 50 | ↓54.3 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #14 / 50 | ↓40.7 | Source ↗official | |
| DystopiaBenchhuxley_score | #17 / 50 | ↓54 | Source ↗official | |
| DystopiaBenchlaguardia_score | #14 / 50 | ↓55.03 | Source ↗official | |
| DystopiaBenchorwell_score | #17 / 50 | ↓53.67 | Source ↗official | |
| DystopiaBenchpetrov_score | #17 / 50 | ↓66.97 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #143 / 272 | ↑15.76 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #249 / 272 | ↑58 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #26 / 272 | ↑98.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #113 / 270 | ↑97.09 | Source ↗official | |
| WildClawBench Safety & Alignment (OpenClaw harness)safety_alignment_score_pct | #18 / 24 | ↑35 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #24 / 272 | ↓58 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #241 / 272 | ↓98.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #155 / 270 | ↓97.09 | Source ↗official |