Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Kimi K2.7 Code

Moonshot · 1T · open weights

Strongest in Language (#35 of 57), weakest in Jailbreak resistance (#222 of 272). Above par in 5 of 19 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5 and GPT-6 Astra and ahead of Kimi K2.6 and DeepSeek V3.2.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Agents52.6#90/268
Knowledge work53.4#60/178
Coding47.5#91/165
Code generation43#58/77
Agentic coding48.7#78/157
Reasoning45.4#126/178
Reasoning51.3#55/140
Mathematics35.9#127/140
Core abilities39.4#191/204
Language47.4#35/57
Data analysis32#53/57
Instruction following29.6#54/57
General intelligence44#143/204
Safety49#207/337
Secure code62.8#37/274
Toxicity avoidance54.8#111/272
Fairness45.9#176/300
Harm refusal46.4#215/300
Jailbreak resistance39.6#222/272

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Kimi K2.7 Code, left for the other.

Qwen3.6 27Bwon 11 · lost 2
Gemini 3.5 Flash Litewon 11 · lost 2
Grok 4.3won 16 · lost 3
Grok Build 0.1won 14 · lost 5
GPT-5.4 Miniwon 10 · lost 4
Command Awon 9 · lost 4
DeepSeek V3won 11 · lost 5
Grok 4.1 Fastwon 8 · lost 4
GPT-4.1 Nanowon 10 · lost 5
GPT-5.4 Nanowon 9 · lost 5
GPT-4o Miniwon 10 · lost 6
GPT-4owon 7 · lost 5
Claude 3.5 Haikuwon 7 · lost 5
MiniMax M3won 11 · lost 8
GLM-4.6won 8 · lost 6
Llama 4 Scout Instructwon 7 · lost 6
Gemini 2.0 Flashwon 7 · lost 6
GPT-4.1 Miniwon 8 · lost 7
DeepSeek V3.2won 8 · lost 7
Kimi K2.6won 10 · lost 9
Claude 3.5 Sonnetwon 6 · lost 6
Gemma 3 27B Itwon 6 · lost 6
GPT-5.1won 6 · lost 7
DeepSeek R1won 7 · lost 9
Gemini 2.5 Prowon 7 · lost 9
Gemma 4 12Bwon 6 · lost 8
GPT OSS 20Bwon 5 · lost 7
GPT OSS 120Bwon 6 · lost 9
GPT-5 Miniwon 6 · lost 9
Kimi K2.5won 6 · lost 9
Qwen3.6 Pluswon 5 · lost 8
Kimi K2 Thinkingwon 5 · lost 8
GLM-5.3 Flashwon 7 · lost 12
GLM-5.2won 7 · lost 12
Qwen3.7 Maxwon 7 · lost 12
O3 Miniwon 5 · lost 9
Gemma 4 31Bwon 5 · lost 9
Grok 4won 5 · lost 9
MiniMax M2.7won 4 · lost 8
Claude Haiku 4.5won 5 · lost 10
Claude Sonnet 4.5won 5 · lost 10
Kimi K2won 4 · lost 10
GPT-4.1won 4 · lost 10
Mimo V2.5 Prowon 4 · lost 10
Gemini 3.1 Prowon 4 · lost 10
Gemini 2.5 Flashwon 4 · lost 11
GPT-5won 4 · lost 11
Inklingwon 5 · lost 14
Gemini 3.6 Flashwon 5 · lost 14
DeepSeek V4 Flashwon 5 · lost 14
Gemini 3.5 Flashwon 5 · lost 14
Claude 3.7 Sonnetwon 3 · lost 9
Claude Sonnet 4won 4 · lost 12
Claude Opus 4.5won 3 · lost 10
Qwen3 235B A22B Instructwon 3 · lost 11
GPT-6 Lunawon 4 · lost 15
O4 Miniwon 3 · lost 12
O3won 3 · lost 12
GPT-5 Nanowon 2 · lost 10
GPT-5.6 Lunawon 3 · lost 16
Muse Spark 1.1won 3 · lost 16
DeepSeek V4 Prowon 3 · lost 16
Gemini 3.8 Flashwon 3 · lost 16
GLM-5.1won 2 · lost 11
Qwen3.8 27Bwon 2 · lost 11
Qwen3.8 Flash Nextwon 2 · lost 11
Claude Opus 4won 2 · lost 12
Claude Sonnet 4.6won 2 · lost 15
GPT-5.2won 2 · lost 16
Claude Sonnet 5won 2 · lost 17
Grok 4.5won 2 · lost 17
Qwen3.8 Maxwon 2 · lost 17
GPT-6 Solwon 2 · lost 17
DeepSeek V4 Flash Visionwon 1 · lost 12
Mimo V2.6 Prowon 1 · lost 13
Claude Opus 4.6won 1 · lost 14
Claude Opus 4.8won 1 · lost 18
Claude Opus 4.7won 1 · lost 18
GPT-5.6 Terrawon 1 · lost 18
GPT-5.4won 1 · lost 18
Grok 4.6won 1 · lost 18
Grok 4.7won 1 · lost 18
GPT-5.6 Solwon 1 · lost 18
Claude Opus 5.5won 1 · lost 18
GPT-5.5won 1 · lost 18
GLM-5.3won 0 · lost 13
Muse Spark 1.2won 0 · lost 13
Gemini 3.7 Flashwon 0 · lost 13
DeepSeek V4.1 Flashwon 0 · lost 13
Kimi K3won 0 · lost 13
Muse Spark 1.3won 0 · lost 13
Claude Fable 5.1won 0 · lost 13
Claude Fable 5won 0 · lost 13
GPT-6 Astrawon 0 · lost 14
Claude Opus 5won 0 · lost 19

§ 3 · Sources

Where the numbers come from

7 publications, 21 figures. Every one links to the page it was read from.

Artificial Analysis ↗1 measureread 2026-09-26
Artificial Analysis Intelligence Index 26
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 1025
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 856
LiveBench ↗8 measuresread 2026-09-26
LiveBench 68.4LiveBench · Reasoning 82.8LiveBench · Coding 74LiveBench · Agentic Coding 45.7LiveBench · Mathematics 79.6LiveBench · Data Analysis 62.7LiveBench · Language 77.9LiveBench · Instruction Following 56.3
SimpleBench ↗1 measureread 2026-09-26
SimpleBench 57.9%
Vals.ai ↗3 measuresread 2026-09-26
Vals · SWE-bench Verified 78.2% (Mini-SWE-agent)Vals · Vibe Code Bench 47.21% (OpenHands)Vals · Code Migration 25.39%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26
Enkrypt · Jailbreak risk 21.6%Enkrypt · Harmful content risk 1.7%Enkrypt · CBRN risk 42%Enkrypt · Toxicity risk 2.9%Enkrypt · Bias risk 84.2%Enkrypt · Insecure code risk 7.6%

Badge

PublicAI Index badge for Kimi K2.7 Code[![PublicAI Index](https://publicai.io/model-index/badge?model=kimi-k2-7-code)](https://publicai.io/model-index/m/kimi-k2-7-code)