Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Magistral Small 1.2

Mistral

Strongest in Mathematics (#63 of 140, on 1 of its 2 boards), weakest in Agents (#222 of 268). Above par in 1 of 11 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5 and Claude Fable 5 and ahead of Mistral Small 3.1 and Mercury 2.5.

§ 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.

Reasoning47.7#102/178
Mathematics53.8#63/140
Science37.6#102/122
Knowledge30.1#135/138
Academic knowledge26.1#120/123
Professional42.2#147/168
Medical49.4#83/140
Finance41.1#125/151
Legal35#150/151
Agents41.7#222/268
Knowledge work37.6#142/178

§ 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 Magistral Small 1.2, left for the other.

Jamba 1.6 Miniwon 8 · lost 1
Jamba 1.6 Largewon 8 · lost 1
Command R Pluswon 6 · lost 1
Llama 4 Scout Instructwon 8 · lost 3
GPT-4.1 Nanowon 8 · lost 3
GPT-4o Miniwon 7 · lost 3
Gemini 1.5 Prowon 6 · lost 3
Mistral Smallwon 6 · lost 3
Mistral Medium 3.5won 7 · lost 4
Gemini 1.5 Flashwon 5 · lost 3
Laguna M.1won 5 · lost 3
Laguna XS.2won 5 · lost 3
Mercury 2.5won 5 · lost 3
Mistral Small 3.1won 6 · lost 5
Mistral Medium 3.1won 5 · lost 5
Command Awon 5 · lost 5
DeepSeek V3won 5 · lost 6
Llama 4 Maverick Instructwon 5 · lost 6
Gemini 2.0 Flashwon 4 · lost 5
Mistral Largewon 4 · lost 5
DeepSeek R1won 4 · lost 6
Claude 3.5 Haikuwon 4 · lost 6
Grok 2won 3 · lost 5
Llama 3.3 Instruct Turbo (70B)won 3 · lost 5
GPT-4owon 3 · lost 6
Nemotron 3 Ultrawon 3 · lost 7
Gemini 2.5 Flash Litewon 3 · lost 7
Llama 3.3 Nemotron Superwon 2 · lost 5
Qwen3.6 27Bwon 2 · lost 5
O3 Miniwon 3 · lost 8
Mistral Large 3won 3 · lost 8
Gemini 3.5 Flash Litewon 3 · lost 8
Grok 4.3won 3 · lost 8
Mimo V2.5won 3 · lost 8
Mimo V2.5 Prowon 3 · lost 8
Kimi K2.6won 3 · lost 8
Qwen3.8 27Bwon 3 · lost 8
Claude 3.5 Sonnetwon 2 · lost 6
Grok 3won 2 · lost 7
Claude Opus 4won 2 · lost 7
DeepSeek V4won 2 · lost 7
MiniMax M2.1won 2 · lost 7
Claude 3.7 Sonnetwon 2 · lost 8
GPT-5.4 Miniwon 2 · lost 8
GPT-5 Nanowon 2 · lost 8
GPT-4.1won 2 · lost 8
Gemini 2.5 Flashwon 2 · lost 8
Kimi K2won 2 · lost 8
Gemini 3.1 Flash Litewon 2 · lost 9
Claude Sonnet 4won 2 · lost 9
GPT-4.1 Miniwon 2 · lost 9
Inkling Smallwon 2 · lost 9
Inklingwon 2 · lost 9
Qwen3.6 Pluswon 2 · lost 9
Qwen3.7 Maxwon 2 · lost 9
MiniMax M3won 2 · lost 9
GLM-5.3 Flashwon 2 · lost 9
GPT-6 Lunawon 1 · lost 7
Grok 4.7won 1 · lost 7
O1won 1 · lost 8
Claude Opus 4.1won 1 · lost 8
Qwen3 Maxwon 1 · lost 8
Qwen3.5 Flashwon 1 · lost 8
Grok 4.20won 1 · lost 8
Ling 3.0 Flashwon 1 · lost 9
Qwen3 235B A22B Instructwon 1 · lost 9
O4 Miniwon 1 · lost 9
Muse Spark 1.2won 1 · lost 9
Grok 4.1 Fastwon 1 · lost 9
Magistral Medium 1.2won 1 · lost 10
Gemini 3.1 Prowon 1 · lost 10
GPT-5.4 Nanowon 1 · lost 10
MiniMax M2.7won 1 · lost 10
Gemini 3.5 Flashwon 1 · lost 10
GLM-4.7won 1 · lost 10
GLM-5.1won 1 · lost 10
Grok 4.5won 1 · lost 10
Claude Haiku 4.5won 1 · lost 10
Gemini 3.6 Flashwon 1 · lost 10
Muse Spark 1.1won 1 · lost 10
GLM-5.2won 1 · lost 10
Claude Sonnet 4.6won 1 · lost 10
Gemini 3.8 Flashwon 1 · lost 10
DeepSeek V4 Flashwon 1 · lost 10
GPT-5.6 Lunawon 1 · lost 10
Kimi K3won 1 · lost 10
GLM-5.3won 1 · lost 10
Grok 4.6won 1 · lost 10
Qwen3.8 Maxwon 1 · lost 10
Mimo V2.6 Prowon 0 · lost 7
Muse Spark 1.3won 0 · lost 7
Gemma 4 31Bwon 0 · lost 8
GPT-6 Solwon 0 · lost 8
GPT-6 Astrawon 0 · lost 8
Claude Opus 5.5won 0 · lost 8
Grok 3 Miniwon 0 · lost 9
Kimi K2 Thinkingwon 0 · lost 9
GLM-4.5won 0 · lost 9
MiniMax M2.5won 0 · lost 9
GLM-5won 0 · lost 9
Grok 4 Fastwon 0 · lost 9
Qwen 3.5 Pluswon 0 · lost 9
Gemini 3 Flashwon 0 · lost 9
Claude Opus 4.6won 0 · lost 9
O3won 0 · lost 10
GPT-5.2won 0 · lost 10
Grok 4won 0 · lost 10
DeepSeek V4.1 Flashwon 0 · lost 10
Gemini 3 Prowon 0 · lost 10
Claude Opus 4.5won 0 · lost 10
Gemini 2.5 Prowon 0 · lost 11
GPT OSS 20Bwon 0 · lost 11
GPT OSS 120Bwon 0 · lost 11
Muse Sparkwon 0 · lost 11
GPT-5 Miniwon 0 · lost 11
GPT-5.1won 0 · lost 11
GPT-5won 0 · lost 11
Kimi K2.5won 0 · lost 11
DeepSeek V3.2won 0 · lost 11
GPT-5.4won 0 · lost 11
Gemini 3.7 Flashwon 0 · lost 11
GPT-5.5won 0 · lost 11
Claude Sonnet 4.5won 0 · lost 11
Claude Opus 4.7won 0 · lost 11
GLM-4.6won 0 · lost 11
DeepSeek V4 Prowon 0 · lost 11
Claude Opus 4.8won 0 · lost 11
GPT-5.6 Terrawon 0 · lost 11
Claude Sonnet 5won 0 · lost 11
GPT-5.6 Solwon 0 · lost 11
Claude Fable 5.1won 0 · lost 11
Claude Fable 5won 0 · lost 11
Claude Opus 5won 0 · lost 11

§ 3 · Sources

Where the numbers come from

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

GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA -10
Vals.ai ↗8 measuresread 2026-09-26
Vals · LegalBench 40.02%Vals · CorpFin 44.02%Vals · TaxEval 60.3%Vals · MortgageTax 62.12%Vals · MedQA 82.36%Vals · GPQA Diamond 58.33%Vals · MMLU Pro 62.13%Vals · AIME 80.68%

Badge

PublicAI Index badge for Magistral Small 1.2[![PublicAI Index](https://publicai.io/model-index/badge?model=magistral-small-1-2)](https://publicai.io/model-index/m/magistral-small-1-2)