The LLM benchmark aggregator.

Kimi K2

Moonshot · 1T · open weights

Strongest in Tool use (#9 of 81), weakest in Toxicity avoidance (#242 of 268). Above par in 13 of 26 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Fable 5 and ahead of GPT OSS 120B and NVIDIA Nemotron 3 Ultra 550B A55B.

§ 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.

Agents56.4−10#40/2981/6

Tool use65.4−8.6#9/811/1

Coding53.3−12.9#55/1791/6

Agentic coding53.6−13.3#51/1731/5

Core abilities49.8−15.5#102/1991/4

General intelligence49.7−19.7#92/1781/3

Professional49.1−13.3#108/1941/2

Legal52.4−13.5#74/1731/1

Medical50.2−16.3#83/1491/1

Finance46−16.4#119/1621/1

Human preference58.4−10.4#111/3541/1

Knowledge49−13.5#128/1971/3

Academic knowledge47.7−16.2#90/1231/1

Safety51.8−9.6#135/3293/3

Safe-prompt compliance59.1−1.3#10/821/1

Harm refusal57.4−4.1#28/2922/2

Secure code62.9−3.3#31/2701/1

Fairness54.3−15.7#74/2922/2

Factual grounding29.8−40.9#95/1041/1

Jailbreak resistance37.6−27.4#224/2681/1

Toxicity avoidance36.8−22.2#242/2681/1

Reasoning44.8−20.6#144/1952/5

Science46.8−16.7#87/1221/1

Mathematics49.1−14.7#90/1521/2

Reasoning38.9−30.1#125/1471/3

§ 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, left for the other.

Gemini 2.0 Flashwon 21 · lost 2

Gemini 1.5 Flashwon 15 · lost 2

Mistral Medium 3.5won 14 · lost 2

GPT-4o miniwon 20 · lost 3

Llama 3.3 70B Instructwon 17 · lost 3

Gemini 1.5 Prowon 16 · lost 3

GPT-4.1 nanowon 21 · lost 4

Command R+won 15 · lost 3

Llama 4 Scout Instructwon 20 · lost 4

Command Awon 20 · lost 4

GPT OSS 20Bwon 16 · lost 5

Magistral Small 1.2won 12 · lost 4

Claude 3.5 Haikuwon 14 · lost 5

Mistral Large 3won 14 · lost 5

GPT-4.1 miniwon 18 · lost 7

Gemini 2.5 Flash-Litewon 14 · lost 6

Llama 4 Maverick Instructwon 18 · lost 8

GPT-4owon 15 · lost 8

Gemma 4 31Bwon 13 · lost 7

Ling 3.0 Flashwon 11 · lost 6

DeepSeek V3won 16 · lost 9

GPT-5.4 nanowon 12 · lost 7

O3 Miniwon 13 · lost 9

Inkling Smallwon 10 · lost 7

DeepSeek V3.1won 9 · lost 7

Claude 3.5 Sonnetwon 11 · lost 9

MiMo V2.5 Prowon 11 · lost 9

Kimi K2.6won 12 · lost 10

Grok 3won 13 · lost 11

GPT-4.1won 14 · lost 12

Gemini 3.5 Flash-Litewon 9 · lost 8

DeepSeek V3.2won 12 · lost 11

NVIDIA Nemotron 3 Ultra 550B A55Bwon 12 · lost 11

GPT OSS 120Bwon 13 · lost 12

MiniMax M2.1won 8 · lost 8

Qwen3.7 Maxwon 11 · lost 11

Claude Haiku 4.5won 12 · lost 12

Grok 4.1 Fastwon 11 · lost 12

MiniMax M3won 11 · lost 12

GLM-5.3 Flashwon 11 · lost 12

MiniMax M2.7won 10 · lost 11

Grok 4.3won 10 · lost 11

GLM-4.7won 8 · lost 9

GPT-5 nanowon 11 · lost 13

Gemini 3.5 Flashwon 10 · lost 12

Gemini 3.6 Flashwon 10 · lost 12

Mistral Large 4won 9 · lost 11

GPT-5.4 miniwon 8 · lost 10

Grok 4won 11 · lost 14

GLM-5.1won 9 · lost 12

O4 Miniwon 11 · lost 15

Gemini 2.5 Flashwon 11 · lost 15

Qwen3.8 27Bwon 7 · lost 10

DeepSeek V4 Flashwon 9 · lost 13

Gemini 3.1 Flash-Litewon 7 · lost 11

GPT-6 Lunawon 8 · lost 13

Grok 4.20won 6 · lost 10

GLM-4.6won 9 · lost 15

Claude Sonnet 4won 9 · lost 16

GLM-5.2won 8 · lost 15

MiniMax M2.5won 6 · lost 12

Grok 4 Fastwon 6 · lost 12

Claude Sonnet 4.6won 7 · lost 14

Claude 3.7 Sonnetwon 7 · lost 15

GLM-4.5won 6 · lost 13

GPT-5 miniwon 8 · lost 18

Inklingwon 7 · lost 16

DeepSeek R1won 7 · lost 17

Kimi K2.5won 7 · lost 17

O1won 6 · lost 15

Gemini 2.5 Prowon 7 · lost 18

Qwen3 235B A22B Instructwon 7 · lost 19

MiMo V2.6 Flashwon 5 · lost 14

GPT-5.6 Lunawon 6 · lost 17

Gemini 3 Prowon 6 · lost 17

Gemini 3.8 Flashwon 6 · lost 17

Gemini 3 Flashwon 4 · lost 12

Grok 3 Miniwon 5 · lost 15

DeepSeek V4 Prowon 6 · lost 18

GLM-5won 4 · lost 14

Gemini 3.1 Prowon 4 · lost 14

Qwen3.8 Maxwon 5 · lost 18

GPT-5.4won 5 · lost 19

Kimi K2 Thinkingwon 4 · lost 16

GPT-5.2won 5 · lost 20

Claude Sonnet 4.5won 5 · lost 21

GPT-6 Solwon 4 · lost 17

Muse Spark 1.1won 4 · lost 17

Claude Opus 4.6won 4 · lost 17

Gemini 3.7 Flashwon 3 · lost 13

Kimi K3won 3 · lost 14

Grok 4.5won 4 · lost 19

Claude Opus 4won 4 · lost 20

GPT-5won 4 · lost 21

Claude Opus 4.5won 3 · lost 17

MiMo V2.6 Prowon 3 · lost 17

GPT-5.1won 3 · lost 19

Grok 4.6won 3 · lost 20

GPT-5.6 Solwon 3 · lost 21

Claude Opus 4.7won 3 · lost 21

O3won 3 · lost 22

GPT-6 Astrawon 2 · lost 15

Claude Sonnet 5won 2 · lost 20

GPT-5.6 Terrawon 2 · lost 21

GPT-5.5won 2 · lost 22

Gemini 4 Argonwon 1 · lost 15

GLM-5.3won 1 · lost 16

Grok 4.7won 1 · lost 19

Claude Opus 5won 1 · lost 21

Claude Opus 4.8won 1 · lost 22

DeepSeek V4.1 Flashwon 0 · lost 17

Claude Fable 5.1won 0 · lost 17

Claude Fable 5won 0 · lost 17

Claude Opus 5.5won 0 · lost 22

§ 3 · Sources

Where the numbers come from

9 publications, 24 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-10

LMArena Text 1418

Aider polyglot ↗1 measureread 2026-11-10

Aider polyglot 59.1%

BFCL ↗1 measureread 2026-11-10

BFCL v4 59.06%

Kagi LLM Benchmark ↗1 measureread 2026-11-10

Kagi LLM Benchmark 52.2%

SimpleBench ↗1 measureread 2026-11-10

SimpleBench 26.3%

Vals.ai ↗7 measuresread 2026-11-10

Vals · LegalBench 81.45%Vals · CorpFin 50.39%Vals · TaxEval 70.2%Vals · MedQA 83.97%Vals · GPQA Diamond 71.46%Vals · MMLU Pro 79.39%Vals · AIME 62.71%

HELM Safety ↗5 measuresread 2026-11-10

HELM Safety · HarmBench 97.4%HELM Safety · SimpleSafetyTests 100%HELM Safety · Anthropic Red Team 99.3%HELM Safety · BBQ 94.9%HELM Safety · XSTest 98.2%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-10

Enkrypt · Jailbreak risk 23.2%Enkrypt · Harmful content risk 15.6%Enkrypt · CBRN risk 12.8%Enkrypt · Toxicity risk 15.2%Enkrypt · Bias risk 74.9%Enkrypt · Insecure code risk 6.7%

Vectara Hallucination Leaderboard ↗1 measureread 2026-11-10

Vectara · Factual consistency 82.1%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=kimi-k2)](https://publicai.io/model-index/m/kimi-k2)