Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Devstral Medium

Mistral

Strongest in General intelligence (#165 of 214, on 1 of its 3 boards), weakest in Core abilities (#166 of 225). Above par in 0 of 2 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of Devstral Small and Granite 4.2 30B.

§ 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 abilities44.9#166/225
General intelligence42.7#165/214

§ 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 Devstral Medium, left for the other.

NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 2 · lost 0
Claude Haiku 4.5won 2 · lost 0
Magistral Smallwon 2 · lost 0
AFM 4.5Bwon 2 · lost 0
Jamba Mini 1.7won 2 · lost 0
Magistral Mediumwon 2 · lost 0
Phi 4 Multimodal Instructwon 2 · lost 0
Spotlightwon 2 · lost 0
Mercury Coderwon 2 · lost 0
UI-TARS 1.5 7Bwon 2 · lost 0
Gemma 4 31Bwon 2 · lost 0
Mercurywon 2 · lost 0
Llama 4 Scout Instructwon 2 · lost 0
K2 Horizon 0.9Bwon 2 · lost 0
Gemma 3 4B Itwon 2 · lost 0
Jamba Large 1.7won 2 · lost 0
NVIDIA Nemotron 3 Ultra 550B A55Bwon 2 · lost 0
Nemotron 3 Nano 4Bwon 2 · lost 0
Ministral 3 3Bwon 2 · lost 0
Ministral 3 8Bwon 2 · lost 0
Ministral 3 14Bwon 2 · lost 0
Celeris 1won 2 · lost 0
Valkyrie 49B V1won 2 · lost 0
GPT-4o Miniwon 2 · lost 0
Command Awon 2 · lost 0
Mistral Small 4won 2 · lost 0
Gemma 3n E4b Itwon 2 · lost 0
Nemotron 3 Nanowon 2 · lost 0
Qwen3 Coder Nextwon 2 · lost 0
Gemma 4 E4Bwon 2 · lost 0
Granite 4.2 3Bwon 2 · lost 0
Virtuoso Largewon 2 · lost 0
Codestralwon 2 · lost 0
North Mini Codewon 2 · lost 0
GPT-4.1 Nanowon 2 · lost 0
Mistral Medium 3.5won 2 · lost 0
Ling 3.0 Tinywon 2 · lost 0
Qwen3.5 9Bwon 2 · lost 0
Granite 4.2 8Bwon 2 · lost 0
Trinity Largewon 2 · lost 0
Claude 3 Haikuwon 2 · lost 0
Llama 3 70B Instructwon 2 · lost 0
Gemma 3 27B Itwon 2 · lost 0
MiniCPM5 2Bwon 2 · lost 0
Mercury 2.5won 2 · lost 0
Qwen2.5 Vl 72B Instructwon 2 · lost 0
Command A+won 2 · lost 0
Granite 4.2 30Bwon 2 · lost 0
Devstral Smallwon 2 · lost 0
GPT-5.4 Miniwon 1 · lost 1
GPT-5.4 Nanowon 1 · lost 1
Nemotron 3.5 Super VLwon 1 · lost 1
Kimi K2.7 Codewon 1 · lost 1
Mistral Large 4won 1 · lost 1
Claude Haiku 5.5won 1 · lost 1
Mistral Smallwon 0 · lost 2
Phi 4 Reasoning Pluswon 0 · lost 2
Gemini 2.0 Flashwon 0 · lost 2
GPT OSS 20Bwon 0 · lost 2
MiniMax M3won 0 · lost 2
Anubis 70B V1.1won 0 · lost 2
K2 Horizon 3.7Bwon 0 · lost 2
Qwen3.5 122B A10Bwon 0 · lost 2
Llama 4 Maverick Instructwon 0 · lost 2
Mistral Small 3.2won 0 · lost 2
Gemma 3 27B It Fastwon 0 · lost 2
Gemini 2.5 Flash Litewon 0 · lost 2
Beam 1.0won 0 · lost 2
Ring 2.6.1Twon 0 · lost 2
Muse Glimmerwon 0 · lost 2
Gemini 3.5 Flash Litewon 0 · lost 2
Muse Spark Openwon 0 · lost 2
Qwen3.6 35B A3Bwon 0 · lost 2
GPT-5.6 Lunawon 0 · lost 2
GLM-4 32Bwon 0 · lost 2
MiniMax 01won 0 · lost 2
GLM-4.5 Airwon 0 · lost 2
LongCat 2.0won 0 · lost 2
GPT-6 Lunawon 0 · lost 2
Longcat Flash Chatwon 0 · lost 2
Inklingwon 0 · lost 2
GPT OSS 120Bwon 0 · lost 2
Nova Premierwon 0 · lost 2
Ernie 4.5 300B A47Bwon 0 · lost 2
Llama 3 405Bwon 0 · lost 2
GLM-4.6won 0 · lost 2
K2 Horizon 7Bwon 0 · lost 2
A.X K2won 0 · lost 2
Nemotron 3.5 Bolt 74B-A9Bwon 0 · lost 2
GLM-5.2won 0 · lost 2
Claude Sonnet 5won 0 · lost 2
Claude Sonnet 4.6won 0 · lost 2
GLM-4.6:exactowon 0 · lost 2
Nemotron Nano 9B V2won 0 · lost 2
Ling 3.0 Flash Finwon 0 · lost 2
GPT-4.1 Miniwon 0 · lost 2
Qwen3 32Bwon 0 · lost 2
Qwen3 14Bwon 0 · lost 2
GLM-5.3 Flashwon 0 · lost 2
Solar Mini 4won 0 · lost 2
Qwen 3 Coderwon 0 · lost 2
DeepSeek V4 Flashwon 0 · lost 2
Mistral Mediumwon 0 · lost 2
Ling 3.0 Flash VLwon 0 · lost 2
K2 Horizon MoVA 36B A4Bwon 0 · lost 2
Hy3won 0 · lost 2
Qwen3.7 Pluswon 0 · lost 2
Mistral Large 3won 0 · lost 2
Step 5won 0 · lost 2
Apodex 1.1won 0 · lost 2
Inkling Smallwon 0 · lost 2
GPT-5.5 Instantwon 0 · lost 2
Nemotron Nano 12B V2 Vlwon 0 · lost 2
Kimi K2won 0 · lost 2
DeepSeek V3.2won 0 · lost 2
Cogito V2 Llama 4 Scoutwon 0 · lost 2
DeepSeek V3won 0 · lost 2
GPT-4.1won 0 · lost 2
DeepSeek R1 Distill Llama 70Bwon 0 · lost 2
Grok Code Fast 1won 0 · lost 2
Quasar 438Bwon 0 · lost 2
Solar Pro4won 0 · lost 2
DeepSeek V3.1won 0 · lost 2
Qwen3 Next 80B A3B Instructwon 0 · lost 2
Qwen3 30B A3B Thinkingwon 0 · lost 2
Qwen3 32B Fastwon 0 · lost 2
Qwen3 235B A22B Instructwon 0 · lost 2
MiniMax M2.5won 0 · lost 2
Hermes 4 405Bwon 0 · lost 2
Qwen3.8 Flashwon 0 · lost 2
Gemini 2.5 Flashwon 0 · lost 2
GPT-5.2won 0 · lost 2
DeepSeek V3.1 Terminuswon 0 · lost 2
K2 Horizon 375B A23Bwon 0 · lost 2
MiniMax M2won 0 · lost 2
Ling 1twon 0 · lost 2
GLM-4.5won 0 · lost 2
Claude Sonnet 4.5won 0 · lost 2
Cogito V2 DeepSeek 671Bwon 0 · lost 2
Qwen3.8 27Bwon 0 · lost 2
GLM-5.3won 0 · lost 2
GLM-4.5vwon 0 · lost 2
Qwen3.5 397B A17Bwon 0 · lost 2
DeepSeek V4 Prowon 0 · lost 2
Cogito V2 Llama 405Bwon 0 · lost 2
JT-4.1 Flash 236B A21Bwon 0 · lost 2
Grok 3won 0 · lost 2
Grok 3 Miniwon 0 · lost 2
Muse Spark 1.2won 0 · lost 2
GPT-5 Nanowon 0 · lost 2
Step 3won 0 · lost 2
Claude Opus 4.5won 0 · lost 2
Qwen Pluswon 0 · lost 2
Kimi K2 Thinkingwon 0 · lost 2
DeepSeek V4 Flash Visionwon 0 · lost 2
Maestro Reasoningwon 0 · lost 2
GPT-5.6 Terrawon 0 · lost 2
Mimo V2.6 Flashwon 0 · lost 2
Claude Opus 4.7won 0 · lost 2
Grok 4 Fastwon 0 · lost 2
Claude Opus 5won 0 · lost 2
Ring 1twon 0 · lost 2
Qwen3 Next 80B A3B Thinkingwon 0 · lost 2
GPT-5.4won 0 · lost 2
Gemini 3.8 Flashwon 0 · lost 2
Gemini 3.1 Flash Litewon 0 · lost 2
O4 Miniwon 0 · lost 2
O3won 0 · lost 2
Qwen3.8 2.4T A95Bwon 0 · lost 2
Claude Opus 4.6won 0 · lost 2
Grok 4.6won 0 · lost 2
Claude 4 Haikuwon 0 · lost 2
Ling 3.1 Flashwon 0 · lost 2
DeepSeek R1won 0 · lost 2
Qwen3 235B A22B Thinkingwon 0 · lost 2
Claude Sonnet 5.5won 0 · lost 2
Gemini 3.7 Flashwon 0 · lost 2
Mimo V2.6 Prowon 0 · lost 2
GPT-5 Miniwon 0 · lost 2
Gemini 2.5 Prowon 0 · lost 2
GPT-5 Codexwon 0 · lost 2
Gemini 3.1 Prowon 0 · lost 2
MiniMax M3.1 Flashwon 0 · lost 2
Qwen3.8 Flash Nextwon 0 · lost 2
Claude Opus 4.8won 0 · lost 2
Qwen3.8 Maxwon 0 · lost 2
O3 Prowon 0 · lost 2
Qwen3 Maxwon 0 · lost 2
Kimi K3won 0 · lost 2
GPT-5won 0 · lost 2
Claude Sonnet 4won 0 · lost 2
Grok 4.5won 0 · lost 2
Grok 4won 0 · lost 2
Claude Opus 4won 0 · lost 2
GPT-6 Solwon 0 · lost 2
Grok 4.20won 0 · lost 2
GLM-5won 0 · lost 2
DeepSeek V4.1 Flashwon 0 · lost 2
Grok 4.7won 0 · lost 2
GPT-5 Prowon 0 · lost 2
Kimi K2.5won 0 · lost 2
GPT-5.6 Solwon 0 · lost 2
Gemini 3 Prowon 0 · lost 2
GPT-5.5won 0 · lost 2
Claude Opus 5.5won 0 · lost 2
Muse Wonderwon 0 · lost 2
Muse Spark 1.3won 0 · lost 2
Muse Wonder Fullwon 0 · lost 2
Claude Fable 5.1won 0 · lost 2
Gemini 4 Argonwon 0 · lost 2
GPT-6.1 Solwon 0 · lost 2
GPT-6 Astrawon 0 · lost 2
Claude Fable 5won 0 · lost 2

§ 3 · Sources

Where the numbers come from

1 publication, 1 figures. Every one links to the page it was read from.

Kagi LLM Benchmark ↗1 measureread 2026-10-19
Kagi LLM Benchmark 37.7%

Badge

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