The LLM benchmark aggregator.

Kimi K2.5

Moonshot · 1T · open weights

Strongest in Computer use (#9 of 37), weakest in Safety (#218 of 337). Above par in 16 of 26 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Gemini 3 Pro and ahead of GPT-4o and Claude 3.5 Sonnet.

§ 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.

Core abilities58.8−8.6#12/2041/3

General intelligence62.6−7.5#10/2041/3

Knowledge54.9−8.6#55/1381/2

Academic knowledge55.9−8#51/1231/1

Human preference61.8−5.7#62/3421/1

Agents54.5−13.6#70/2682/5

Computer use59.4−12.3#9/371/1

Knowledge work51.8−21.8#67/1781/2

Reasoning52.3−14.6#74/1783/4

Mathematics57.8−7.9#19/1401/2

Science55.6−7.9#55/1221/1

Reasoning46.2−22.9#74/1402/3

Professional49.6−12#85/1681/1

Finance53.4−9.5#65/1511/1

Medical50.9−15.9#73/1401/1

Legal43.4−23.7#113/1511/1

Coding43.1−26#132/1651/5

Agentic coding42.3−26.4#127/1571/4

Safety48.7−12.8#218/3372/3

Secure code63.7−2.8#25/2741/1

Factual grounding39.3−31.3#88/1011/1

Toxicity avoidance53.9−5.1#133/2721/1

Fairness46.2−23.8#165/3001/2

Harm refusal48.6−13#177/3001/2

Jailbreak resistance40.6−24.3#215/2721/1

§ 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 K2.5, left for the other.

Mistral Medium 3.5won 17 · lost 0

Grok 4.3won 22 · lost 2

Mistral Smallwon 18 · lost 2

Mistral Large 3won 18 · lost 2

Command R Pluswon 15 · lost 2

GPT-4.1 Nanowon 21 · lost 3

Command Awon 20 · lost 3

GPT OSS 20Bwon 18 · lost 3

GPT-5.4 Nanowon 17 · lost 3

Ling 3.0 Flashwon 15 · lost 3

DeepSeek V3won 20 · lost 5

GPT-5.4 Miniwon 15 · lost 4

GPT-4o Miniwon 18 · lost 5

Mistral Largewon 14 · lost 4

Gemini 1.5 Prowon 14 · lost 4

Grok 4.1 Fastwon 17 · lost 5

Grok 3won 16 · lost 5

Gemini 1.5 Flashwon 12 · lost 4

DeepSeek R1won 18 · lost 6

Llama 4 Scout Instructwon 17 · lost 6

GLM-4.5won 14 · lost 5

Gemini 3.1 Flash Litewon 14 · lost 5

Gemini 2.5 Flash Litewon 13 · lost 5

Grok 4 Fastwon 13 · lost 5

GPT OSS 120Bwon 18 · lost 7

Kimi K2won 17 · lost 7

GLM-4.6won 17 · lost 7

MiniMax M2.5won 11 · lost 5

Gemini 2.0 Flashwon 15 · lost 7

Claude Haiku 4.5won 17 · lost 8

DeepSeek V3.2won 17 · lost 8

Gemma 4 31Bwon 14 · lost 7

GPT-4.1 Miniwon 16 · lost 8

Claude Sonnet 4won 17 · lost 9

Llama 4 Maverick Instructwon 16 · lost 9

GPT-5 Nanowon 14 · lost 8

O3 Miniwon 14 · lost 8

Inkling Smallwon 10 · lost 6

GLM-4.7won 10 · lost 6

Gemini 2.5 Flashwon 15 · lost 9

Qwen3.6 Pluswon 11 · lost 7

Gemini 3.5 Flash Litewon 11 · lost 7

Grok 4won 14 · lost 9

Qwen3 235B A22B Instructwon 14 · lost 9

Mimo V2.5 Prowon 14 · lost 9

Claude 3.5 Haikuwon 12 · lost 8

GPT-5 Miniwon 15 · lost 10

O4 Miniwon 14 · lost 10

MiniMax M3won 14 · lost 11

Gemini 2.5 Prowon 14 · lost 11

Qwen3.8 27Bwon 10 · lost 8

Kimi K2 Thinkingwon 11 · lost 9

DeepSeek V4 Flashwon 13 · lost 11

Claude 3.5 Sonnetwon 10 · lost 9

GPT-4owon 11 · lost 10

GPT-4.1won 12 · lost 12

O3won 12 · lost 12

MiniMax M2.7won 10 · lost 11

Claude 3.7 Sonnetwon 10 · lost 12

O1won 9 · lost 11

Kimi K2.6won 11 · lost 15

Qwen3.7 Maxwon 10 · lost 14

Claude Opus 4won 9 · lost 14

GPT-6 Lunawon 8 · lost 13

GLM-5.2won 9 · lost 15

GLM-5.3 Flashwon 8 · lost 16

Gemini 3.5 Flashwon 8 · lost 16

Gemini 3.6 Flashwon 8 · lost 16

GLM-5.1won 7 · lost 15

DeepSeek V4.1 Flashwon 5 · lost 12

Inklingwon 7 · lost 17

Grok 4.7won 6 · lost 15

GPT-5won 7 · lost 18

GLM-5won 5 · lost 13

Claude Sonnet 4.5won 7 · lost 19

Mimo V2.6 Prowon 5 · lost 14

DeepSeek V4 Prowon 6 · lost 19

GPT-5.6 Lunawon 5 · lost 19

Gemini 3.8 Flashwon 5 · lost 19

Gemini 3.1 Prowon 4 · lost 16

Muse Spark 1.1won 5 · lost 20

Claude Opus 4.6won 4 · lost 17

Muse Spark 1.2won 3 · lost 14

GPT-5.1won 4 · lost 19

GLM-5.3won 3 · lost 15

Gemini 3.7 Flashwon 3 · lost 15

GPT-5.2won 4 · lost 20

Claude Sonnet 5won 4 · lost 20

Grok 4.5won 4 · lost 20

Claude Sonnet 4.6won 4 · lost 20

Qwen3.8 Maxwon 4 · lost 20

Claude Opus 4.5won 3 · lost 16

GPT-6 Solwon 3 · lost 19

Gemini 3 Flashwon 2 · lost 14

Grok 4.6won 3 · lost 21

GPT-5.6 Terrawon 3 · lost 21

Claude Opus 4.8won 3 · lost 21

GPT-5.4won 3 · lost 22

GPT-5.6 Solwon 3 · lost 22

Claude Opus 4.7won 3 · lost 22

Kimi K3won 2 · lost 16

Claude Opus 5won 2 · lost 23

GPT-5.5won 1 · lost 24

GPT-6 Astrawon 0 · lost 17

Claude Fable 5.1won 0 · lost 18

Claude Fable 5won 0 · lost 19

Gemini 3 Prowon 0 · lost 21

Claude Opus 5.5won 0 · lost 21

§ 3 · Sources

Where the numbers come from

9 publications, 29 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26

LMArena Text 1450

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA 824

ARC-AGI-2 ↗1 measureread 2026-09-26

ARC-AGI-2 11.8%

OSWorld ↗1 measureread 2026-09-26

OSWorld 63.3%

Kagi LLM Benchmark ↗1 measureread 2026-09-26

Kagi LLM Benchmark 78.5%

SimpleBench ↗1 measureread 2026-09-26

SimpleBench 46.8%

Vals.ai ↗16 measuresread 2026-09-26

Vals · Legal Research Bench 15.87%Vals · CaseLaw 58.73%Vals · Harvey Legal Agent Benchmark 0%Vals · Finance Agent 35.79%Vals · CorpFin 68.26%Vals · TaxEval 74.2%Vals · MortgageTax 66.53%Vals · MedQA 94.37%Vals · MedCode 39.32%Vals · MedScribe 76.44%Vals · SWE-bench Verified 70% (Mini-SWE-agent)Vals · Vibe Code Bench 17.54% (OpenHands)Vals · Code Migration 6.96%Vals · GPQA Diamond 84.09%Vals · MMLU Pro 85.91%Vals · AIME 95.63%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26

Enkrypt · Jailbreak risk 20.7%Enkrypt · Harmful content risk 5.6%Enkrypt · CBRN risk 33.2%Enkrypt · Toxicity risk 3.6%Enkrypt · Bias risk 83.7%Enkrypt · Insecure code risk 5.8%

Vectara Hallucination Leaderboard ↗1 measureread 2026-09-26

Vectara · Factual consistency 85.8%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=kimi-k2-5)](https://publicai.io/model-index/m/kimi-k2-5)