Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Mistral Medium

Mistral

Strongest in Tool use (#35 of 81), weakest in Safety (#311 of 336). Above par in 2 of 8 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 3 Pro and Claude Opus 4.5 and ahead of GPT-5.4 Nano and Mistral Medium 3.5.

§ 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 abilities49.1#106/204
General intelligence48.7#110/204
Human preference57.8#118/341
Human preference57.8#118/341
Agents49.9#120/267
Tool use49.9#35/81
Safety42.5#311/336
Factual grounding26#98/101

§ 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 Mistral Medium, left for the other.

Ministral 3 3Bwon 5 · lost 0
Granite 4.2 30Bwon 5 · lost 0
Granite 4.2 8Bwon 6 · lost 0
Granite 4.2 3Bwon 6 · lost 0
GPT-4.1 Nanowon 6 · lost 1
GPT-4o Miniwon 5 · lost 1
GPT OSS 20Bwon 5 · lost 1
Llama 3.2 1B Instructwon 4 · lost 1
Llama 3.2 3B Instructwon 4 · lost 1
Granite 3.1 8B Instructwon 4 · lost 1
Llama 3.1 8B Instructwon 4 · lost 1
Claude 3 Haikuwon 4 · lost 1
Llama 3 70B Instructwon 4 · lost 1
Magistral Mediumwon 4 · lost 1
Gemini 2.0 Flashwon 4 · lost 1
Gemma 3 4B Itwon 6 · lost 2
Llama 4 Scout Instructwon 6 · lost 2
Mistral Smallwon 6 · lost 2
Gemma 3 27B Itwon 6 · lost 2
Gemini 2.5 Flash Litewon 6 · lost 2
GPT OSS 120Bwon 5 · lost 2
Trinity Largewon 5 · lost 2
GPT-4.1 Miniwon 5 · lost 2
Ministral 8Bwon 4 · lost 2
Nova Microwon 4 · lost 2
Phi 4won 4 · lost 2
Nova Prowon 4 · lost 2
Nova 2 Litewon 4 · lost 2
Gemma 3 12B Itwon 4 · lost 2
GLM-4.5 Airwon 4 · lost 2
Qwen3 32Bwon 5 · lost 3
Ministral 3 8Bwon 3 · lost 2
Ministral 3 14Bwon 3 · lost 2
Mercury 2won 3 · lost 2
Qwen3 30B A3B Instructwon 3 · lost 2
Qwen3.5 35B A3Bwon 3 · lost 2
Muse Glimmerwon 3 · lost 2
Mistral Medium 3.5won 3 · lost 2
GPT-5.4 Nanowon 4 · lost 3
Qwen3 14Bwon 3 · lost 3
Llama 4 Maverick Instructwon 4 · lost 4
Command Awon 4 · lost 4
Qwen3 Next 80B A3B Thinkingwon 3 · lost 4
DeepSeek V3won 3 · lost 4
Claude Sonnet 4won 3 · lost 4
Mistral Large 3won 3 · lost 4
Qwen3.5 122B A10Bwon 3 · lost 4
MiniMax M3won 3 · lost 4
Inklingwon 3 · lost 4
MiniMax M2won 2 · lost 3
Grok 3 Miniwon 2 · lost 3
Qwen3.6 Pluswon 2 · lost 3
Gemini 3.5 Flash Litewon 2 · lost 3
Mistral Largewon 2 · lost 4
Grok 4 Fastwon 2 · lost 4
Grok 4.3won 2 · lost 4
GPT-5.4 Miniwon 2 · lost 5
GPT-5.6 Lunawon 2 · lost 5
Kimi K2.6won 2 · lost 5
Claude Sonnet 4.6won 2 · lost 5
GPT-5 Nanowon 2 · lost 6
GPT-5 Miniwon 2 · lost 6
O4 Miniwon 2 · lost 6
Claude Haiku 4.5won 2 · lost 6
GLM-4.6won 2 · lost 6
Gemma 4 31Bwon 2 · lost 6
DeepSeek V3.1 Terminuswon 1 · lost 4
Gemma 4 26B A4Bwon 1 · lost 4
Grok 4.1 Fastwon 1 · lost 5
GPT-6 Lunawon 1 · lost 5
Qwen3.5 397B A17Bwon 1 · lost 5
GLM-5.3 Flashwon 1 · lost 5
Qwen3.7 Maxwon 1 · lost 5
Gemini 3.6 Flashwon 1 · lost 5
Muse Spark 1.1won 1 · lost 5
DeepSeek R1won 1 · lost 6
Gemini 3.1 Flash Litewon 1 · lost 6
Gemini 2.5 Prowon 1 · lost 6
Claude Sonnet 5won 1 · lost 6
GLM-5.2won 1 · lost 6
Gemini 3.1 Prowon 1 · lost 6
GLM-4.5won 0 · lost 5
GPT-5.1won 0 · lost 5
Qwen3.7 Pluswon 0 · lost 5
GPT-5.5 Instantwon 0 · lost 5
DeepSeek V4.1 Flashwon 0 · lost 5
GLM-5.3won 0 · lost 5
Gemini 3.7 Flashwon 0 · lost 5
Kimi K3won 0 · lost 5
Muse Spark 1.3won 0 · lost 5
Muse Spark 1.2won 0 · lost 5
Claude Fable 5.1won 0 · lost 5
Claude Fable 5won 0 · lost 5
Grok 3won 0 · lost 6
DeepSeek V3.1won 0 · lost 6
Claude Opus 4won 0 · lost 6
Qwen3.8 27Bwon 0 · lost 6
Grok 4.7won 0 · lost 6
DeepSeek V4 Flashwon 0 · lost 6
Grok 4.6won 0 · lost 6
Hy3won 0 · lost 6
GLM-5won 0 · lost 6
Grok 4.5won 0 · lost 6
Mimo V2.5 Prowon 0 · lost 6
Gemini 3.5 Flashwon 0 · lost 6
Qwen3.8 Maxwon 0 · lost 6
Mimo V2.6 Prowon 0 · lost 6
Claude Opus 4.8won 0 · lost 6
Claude Opus 5won 0 · lost 6
Gemini 3.8 Flashwon 0 · lost 6
Claude Opus 4.6won 0 · lost 6
Claude Opus 5.5won 0 · lost 6
Grok 4won 0 · lost 7
O3won 0 · lost 7
GPT-5won 0 · lost 7
Kimi K2.5won 0 · lost 7
GPT-6 Solwon 0 · lost 7
DeepSeek V4 Prowon 0 · lost 7
GPT-5.6 Terrawon 0 · lost 7
GPT-5.4won 0 · lost 7
GPT-6 Astrawon 0 · lost 7
GPT-5.5won 0 · lost 7
GPT-5.6 Solwon 0 · lost 7
Claude Opus 4.7won 0 · lost 7
Gemini 2.5 Flashwon 0 · lost 8
GPT-4.1won 0 · lost 8
Kimi K2won 0 · lost 8
Qwen3 235B A22B Instructwon 0 · lost 8
DeepSeek V3.2won 0 · lost 8
GPT-5.2won 0 · lost 8
Claude Sonnet 4.5won 0 · lost 8
Claude Opus 4.5won 0 · lost 8
Gemini 3 Prowon 0 · lost 8

§ 3 · Sources

Where the numbers come from

4 publications, 4 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-27
LMArena Text 1408
BFCL ↗1 measureread 2026-09-27
BFCL v4 37.69%
Kagi LLM Benchmark ↗1 measureread 2026-09-27
Kagi LLM Benchmark 50%
Vectara Hallucination Leaderboard ↗1 measureread 2026-09-27
Vectara · Factual consistency 77.3%

Badge

PublicAI Index badge for Mistral Medium[![PublicAI Index](https://publicai.io/model-index/badge?model=mistral-medium)](https://publicai.io/model-index/m/mistral-medium)