Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Mistral Medium 3.5

Mistral

Strongest in Human preference (#95 of 342), weakest in Reasoning (#169 of 178). Above par in 2 of 17 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Opus 4.7 and ahead of GPT-4.1 Nano and Mistral Small.

§ 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.

Human preference59.5#95/342
Human preference59.5#95/342
Knowledge43.9#112/138
Academic knowledge42.6#101/123
Coding40.5#148/165
Agentic coding39.5#145/157
Agents47.2#149/268
Knowledge work46.4#99/178
Professional38.8#159/168
Medical39.9#125/140
Finance39.7#130/151
Legal34.8#151/151
Core abilities43.7#164/204
General intelligence42#159/204
Reasoning35.9#169/178
Mathematics37.7#116/140
Science26.1#117/122

§ 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 3.5, left for the other.

GPT-4o Miniwon 13 · lost 3
Mercury 2.5won 9 · lost 3
Llama 4 Scout Instructwon 10 · lost 5
Claude 3.5 Haikuwon 9 · lost 5
Command Awon 10 · lost 6
Mistral Small 3.1won 6 · lost 5
Granite 4.2 3Bwon 6 · lost 5
Mistral Smallwon 7 · lost 6
GPT-4.1 Nanowon 9 · lost 8
GPT-4owon 6 · lost 7
Qwen3.6 27Bwon 5 · lost 6
Mistral Largewon 5 · lost 6
Gemini 1.5 Prowon 5 · lost 6
GPT OSS 20Bwon 6 · lost 9
Magistral Small 1.2won 4 · lost 7
Magistral Medium 1.2won 4 · lost 7
Mistral Large 3won 6 · lost 11
O3 Miniwon 4 · lost 11
Grok 4 Fastwon 4 · lost 11
Claude 3.5 Sonnetwon 3 · lost 9
DeepSeek R1won 4 · lost 12
DeepSeek V3won 4 · lost 13
GPT-5.4 Nanowon 4 · lost 13
Gemini 3.1 Flash Litewon 4 · lost 13
Grok 4.3won 4 · lost 13
Claude 3.7 Sonnetwon 3 · lost 11
Inkling Smallwon 3 · lost 12
GPT-4.1 Miniwon 3 · lost 14
GPT-5 Miniwon 3 · lost 14
Gemini 3.5 Flash Litewon 3 · lost 14
Ling 3.0 Flashwon 2 · lost 10
MiniMax M2.1won 2 · lost 11
Qwen3.5 Flashwon 2 · lost 11
O1won 2 · lost 11
GLM-4.5won 2 · lost 11
Grok 3won 2 · lost 11
Nemotron 3 Ultrawon 2 · lost 12
GPT-5 Nanowon 2 · lost 12
Grok 3 Miniwon 2 · lost 12
Gemini 2.5 Flash Litewon 2 · lost 12
Grok 4.1 Fastwon 2 · lost 12
Gemma 4 31Bwon 2 · lost 12
Gemini 2.0 Flashwon 2 · lost 13
MiniMax M2.5won 2 · lost 13
MiniMax M2.7won 2 · lost 13
Qwen3 235B A22B Instructwon 2 · lost 13
Qwen3 Maxwon 2 · lost 13
O4 Miniwon 2 · lost 14
Gemini 2.5 Flashwon 2 · lost 14
Grok 4won 2 · lost 14
GPT-4.1won 2 · lost 14
Kimi K2won 2 · lost 14
GPT-5.4 Miniwon 2 · lost 14
GPT OSS 120Bwon 2 · lost 15
Claude Sonnet 4won 2 · lost 15
Claude Haiku 4.5won 2 · lost 15
GLM-4.6won 2 · lost 15
DeepSeek V3.2won 2 · lost 15
Qwen3.6 Pluswon 2 · lost 15
Gemini 2.5 Prowon 2 · lost 15
Gemini 3.1 Prowon 2 · lost 15
MiniMax M3won 1 · lost 16
Kimi K2.6won 1 · lost 16
GLM-5.3 Flashwon 1 · lost 16
Qwen 3.5 Pluswon 0 · lost 11
DeepSeek V4won 0 · lost 11
Claude Opus 4.1won 0 · lost 11
Qwen3.7 Pluswon 0 · lost 11
Kimi K2 Thinkingwon 0 · lost 13
Grok 4.20won 0 · lost 13
Gemini 3 Flashwon 0 · lost 13
Mimo V2.6 Prowon 0 · lost 13
Muse Spark 1.3won 0 · lost 13
Grok 4.7won 0 · lost 14
GPT-6 Lunawon 0 · lost 14
GPT-6 Solwon 0 · lost 14
GPT-6 Astrawon 0 · lost 14
Claude Opus 5.5won 0 · lost 14
Claude Opus 4won 0 · lost 15
Mimo V2.5won 0 · lost 15
GLM-4.7won 0 · lost 15
GPT-5.1won 0 · lost 15
GLM-5won 0 · lost 15
GLM-5.1won 0 · lost 15
Muse Sparkwon 0 · lost 15
Claude Opus 4.6won 0 · lost 15
O3won 0 · lost 16
GPT-5.2won 0 · lost 16
Claude Opus 4.5won 0 · lost 16
DeepSeek V4.1 Flashwon 0 · lost 16
Gemini 3 Prowon 0 · lost 16
Muse Spark 1.2won 0 · lost 16
GPT-5won 0 · lost 17
Qwen3.8 27Bwon 0 · lost 17
DeepSeek V4 Flashwon 0 · lost 17
Inklingwon 0 · lost 17
Kimi K2.5won 0 · lost 17
Grok 4.6won 0 · lost 17
GPT-5.6 Lunawon 0 · lost 17
Claude Sonnet 4.5won 0 · lost 17
Claude Sonnet 5won 0 · lost 17
DeepSeek V4 Prowon 0 · lost 17
Grok 4.5won 0 · lost 17
GPT-5.6 Terrawon 0 · lost 17
Mimo V2.5 Prowon 0 · lost 17
Claude Sonnet 4.6won 0 · lost 17
Qwen3.7 Maxwon 0 · lost 17
GPT-5.4won 0 · lost 17
GLM-5.2won 0 · lost 17
Gemini 3.5 Flashwon 0 · lost 17
Qwen3.8 Maxwon 0 · lost 17
GLM-5.3won 0 · lost 17
Claude Opus 4.8won 0 · lost 17
GPT-5.5won 0 · lost 17
Gemini 3.6 Flashwon 0 · lost 17
GPT-5.6 Solwon 0 · lost 17
Gemini 3.7 Flashwon 0 · lost 17
Kimi K3won 0 · lost 17
Claude Opus 5won 0 · lost 17
Muse Spark 1.1won 0 · lost 17
Gemini 3.8 Flashwon 0 · lost 17
Claude Fable 5.1won 0 · lost 17
Claude Opus 4.7won 0 · lost 17
Claude Fable 5won 0 · lost 17

§ 3 · Sources

Where the numbers come from

6 publications, 20 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1426
Artificial Analysis ↗1 measureread 2026-09-26
Artificial Analysis Intelligence Index 14
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 747
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 521
Kagi LLM Benchmark ↗1 measureread 2026-09-26
Kagi LLM Benchmark 41.4%
Vals.ai ↗15 measuresread 2026-09-26
Vals · Legal Research Bench 9.13%Vals · CaseLaw 44.16%Vals · Harvey Legal Agent Benchmark 0.42%Vals · Finance Agent 32.1%Vals · CorpFin 58.78%Vals · TaxEval 67.99%Vals · MortgageTax 28.89%Vals · MedCode 33.75%Vals · MedScribe 67.73%Vals · SWE-bench Verified 66.4% (Mini-SWE-agent)Vals · Vibe Code Bench 2.89% (OpenHands)Vals · Code Migration 5.13%Vals · GPQA Diamond 34.85%Vals · MMLU Pro 75.33%Vals · ProofBench 9%

Badge

PublicAI Index badge for Mistral Medium 3.5[![PublicAI Index](https://publicai.io/model-index/badge?model=mistral-medium-3-5)](https://publicai.io/model-index/m/mistral-medium-3-5)