The LLM benchmark aggregator.

Mistral Small 3.2

Mistral · 24B · open weights

Strongest in General intelligence (#152 of 213, on 1 of its 3 boards), weakest in Agents (#263 of 290). Above par in 2 of 6 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 4 Argon and Muse Wonder and ahead of Gemma 3 27B IT 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 abilities45.8−19.4#154/2241/4

General intelligence44−24.8#152/2131/3

Human preference52.5−16.1#166/3501/1

Agents41.7−24.2#263/2901/6

Knowledge work33.3−38.5#186/1991/2

§ 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 Small 3.2, left for the other.

K2 Horizon 0.9Bwon 4 · lost 0

Llama 3.1 8B Instructwon 4 · lost 0

Claude 3 Haikuwon 4 · lost 0

Llama 3 70B Instructwon 4 · lost 0

Magistral Mediumwon 4 · lost 0

Mercurywon 4 · lost 0

Gemma 3n E4B ITwon 4 · lost 0

Gemma 3 12B ITwon 4 · lost 0

Granite 4.2 3Bwon 5 · lost 1

GPT-4.1 nanowon 5 · lost 1

NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)won 5 · lost 1

Gemma 3 4B ITwon 4 · lost 1

Command A (03-2025)won 4 · lost 1

Ministral 3 8Bwon 3 · lost 1

Ministral 3 14Bwon 3 · lost 1

Celeris 1won 3 · lost 1

NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)won 3 · lost 1

Granite 4.2 8Bwon 4 · lost 2

GPT-4o miniwon 4 · lost 2

GPT OSS 20Bwon 4 · lost 2

Llama 4 Scout Instructwon 4 · lost 2

Llama 4 Maverick Instructwon 4 · lost 2

Granite 4.2 30Bwon 4 · lost 2

Gemma 3 27B ITwon 4 · lost 2

Nemotron 3 Nano 4Bwon 2 · lost 2

Ministral 3 3Bwon 2 · lost 2

Mistral Small 4won 2 · lost 2

Qwen3 Coder Nextwon 2 · lost 2

Gemma 4 E4Bwon 2 · lost 2

North Mini Codewon 2 · lost 2

Nemotron 3.5 Super VLwon 2 · lost 2

Ling 3.0 Tinywon 2 · lost 2

Qwen3.5 9Bwon 2 · lost 2

MiniCPM5 2Bwon 2 · lost 2

Mercury 2.5won 2 · lost 2

Command A+won 2 · lost 2

K2 Horizon 3.7Bwon 2 · lost 2

Qwen3 30B A3B Thinkingwon 2 · lost 2

GPT-4won 2 · lost 2

Mistral Small 3.1 24B Instructwon 2 · lost 2

Llama 3.3 70B Instructwon 2 · lost 2

Claude 3.5 Haikuwon 2 · lost 2

Amazon Nova 2 Litewon 2 · lost 2

GPT-4owon 2 · lost 2

Mercury 2won 2 · lost 2

MiniMax M2won 2 · lost 2

Qwen Pluswon 2 · lost 2

Step 3won 2 · lost 2

GLM-4.5Vwon 2 · lost 2

Gemini 2.0 Flashwon 2 · lost 2

NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)won 3 · lost 3

Gemma 4 31Bwon 3 · lost 3

Mistral Mediumwon 2 · lost 3

GPT-5 nanowon 2 · lost 3

Qwen3 32Bwon 2 · lost 4

GPT OSS 120Bwon 2 · lost 4

Trinity Largewon 2 · lost 4

DeepSeek V3won 2 · lost 4

GPT-5.4 nanowon 2 · lost 4

Claude Haiku 4.5won 2 · lost 4

Qwen3.5 122B A10Bwon 2 · lost 4

Mistral Medium 3.5won 2 · lost 4

GPT-5.4 miniwon 2 · lost 4

Kimi K2.7 Codewon 1 · lost 3

Claude Haiku 5.5won 1 · lost 3

O3 Miniwon 1 · lost 3

Grok 4.3won 1 · lost 4

Qwen3.6 Pluswon 1 · lost 4

Qwen3 235B A22B Thinkingwon 1 · lost 5

DeepSeek R1won 1 · lost 5

Mistral Large 4won 1 · lost 5

Inklingwon 1 · lost 5

MiniMax M3won 1 · lost 5

Beam 1.0won 0 · lost 4

Ring 2.6.1Twon 0 · lost 4

Muse Spark Openwon 0 · lost 4

Qwen3.6 35B A3Bwon 0 · lost 4

LongCat 2.0won 0 · lost 4

K2 Horizon 7Bwon 0 · lost 4

A.X K2won 0 · lost 4

Nemotron 3.5 Bolt 74B-A9Bwon 0 · lost 4

Ling 3.0 Flash Finwon 0 · lost 4

Qwen3 14Bwon 0 · lost 4

Solar Mini 4won 0 · lost 4

Ling 3.0 Flash VLwon 0 · lost 4

K2 Horizon MoVA 36B A4Bwon 0 · lost 4

Apodex 1.1won 0 · lost 4

K2 Horizon 375B A23Bwon 0 · lost 4

JT-4.1 Flash 236B A21Bwon 0 · lost 4

DeepSeek V4 Flash Visionwon 0 · lost 4

MiniMax M3.1 Flashwon 0 · lost 4

Qwen3.8 2.4T A95Bwon 0 · lost 4

Ling 3.1 Flashwon 0 · lost 4

Qwen3.8 Flash Nextwon 0 · lost 4

Muse Wonder Fullwon 0 · lost 4

Grok 3 Miniwon 0 · lost 4

GLM-4.5 Airwon 0 · lost 4

MiMo V2 Flashwon 0 · lost 4

Solar Pro 4won 0 · lost 4

MiniMax M2.5won 0 · lost 4

Qwen3.5 35B A3Bwon 0 · lost 4

Qwen3 Next 80B A3B Instructwon 0 · lost 4

LongCat Flash Chatwon 0 · lost 4

Grok 4 Fastwon 0 · lost 4

Mistral Medium 3.1won 0 · lost 4

GLM-4.5won 0 · lost 4

Grok 3won 0 · lost 4

MiniMax M2.7won 0 · lost 4

DeepSeek V3.1won 0 · lost 4

Qwen3 Maxwon 0 · lost 4

Claude Opus 4won 0 · lost 4

MiMo V2.5won 0 · lost 4

Gemma 4 26B A4Bwon 0 · lost 4

GLM-4.7won 0 · lost 4

GPT-5.1won 0 · lost 4

GLM-5won 0 · lost 4

GLM-5.1won 0 · lost 4

MiMo V2.5 Prowon 0 · lost 4

Grok 4.20 (Reasoning, 0309)won 0 · lost 4

Muse Sparkwon 0 · lost 4

Claude Opus 4.6won 0 · lost 4

NVIDIA Nemotron 3 Super 120B A12Bwon 0 · lost 5

Gemini 2.5 Flash-Litewon 0 · lost 5

O4 Miniwon 0 · lost 5

Gemini 2.5 Flashwon 0 · lost 5

Grok 4won 0 · lost 5

GPT-4.1won 0 · lost 5

Kimi K2won 0 · lost 5

Qwen3 235B A22B Instructwon 0 · lost 5

O3won 0 · lost 5

GPT-5.2won 0 · lost 5

Kimi K2.6won 0 · lost 5

Qwen3.7 Maxwon 0 · lost 5

Claude Opus 4.5 (High, 32K, 20251101)won 0 · lost 5

Gemini 3.5 Flashwon 0 · lost 5

Gemini 3.6 Flashwon 0 · lost 5

Gemini 3 Prowon 0 · lost 5

Muse Spark 1.1won 0 · lost 5

Qwen3 Next 80B A3B Thinkingwon 0 · lost 6

GPT-4.1 miniwon 0 · lost 6

GPT-5 miniwon 0 · lost 6

Claude Sonnet 4won 0 · lost 6

Inkling Smallwon 0 · lost 6

Mistral Large 3won 0 · lost 6

DeepSeek V3.1 Terminuswon 0 · lost 6

DeepSeek V3.2won 0 · lost 6

GLM-4.6won 0 · lost 6

Muse Glimmerwon 0 · lost 6

Gemini 3.1 Flash-Litewon 0 · lost 6

GPT-5won 0 · lost 6

Qwen3.8 27Bwon 0 · lost 6

DeepSeek V4 Flashwon 0 · lost 6

GPT-6 Lunawon 0 · lost 6

Qwen3.5 397B A17Bwon 0 · lost 6

Grok 4.7won 0 · lost 6

Gemini 2.5 Prowon 0 · lost 6

Step 5won 0 · lost 6

MiMo V2.6 Flashwon 0 · lost 6

Kimi K2.5won 0 · lost 6

GPT-5.6 Lunawon 0 · lost 6

Hy3won 0 · lost 6

Grok 4.6won 0 · lost 6

Gemini 3.5 Flash-Litewon 0 · lost 6

Qwen3.7 Pluswon 0 · lost 6

Claude Sonnet 4.5 (High, 32K, 20250929)won 0 · lost 6

GPT-6 Solwon 0 · lost 6

Claude Sonnet 5won 0 · lost 6

DeepSeek-V4-Pro (High, 20260813)won 0 · lost 6

Grok 4.5won 0 · lost 6

GPT-5.6 Terrawon 0 · lost 6

Claude Sonnet 4.6won 0 · lost 6

GPT-5.5 Instantwon 0 · lost 6

DeepSeek V4.1 Flashwon 0 · lost 6

GLM-5.3 Flashwon 0 · lost 6

GPT-5.4won 0 · lost 6

GPT-6 Astrawon 0 · lost 6

GLM-5.2won 0 · lost 6

Claude Sonnet 5.5won 0 · lost 6

GPT-6.1 Solwon 0 · lost 6

MiMo V2.6 Prowon 0 · lost 6

GLM-5.3won 0 · lost 6

Claude Opus 4.8won 0 · lost 6

GPT-5.5won 0 · lost 6

Qwen3.8 Maxwon 0 · lost 6

GPT-5.6 Solwon 0 · lost 6

Gemini 3.1 Prowon 0 · lost 6

Kimi K3won 0 · lost 6

Gemini 3.7 Flashwon 0 · lost 6

Claude Opus 5won 0 · lost 6

Muse Spark 1.2won 0 · lost 6

Muse Spark 1.3won 0 · lost 6

Gemini 3.8 Flashwon 0 · lost 6

Claude Opus 4.7won 0 · lost 6

Claude Fable 5.1won 0 · lost 6

Claude Fable 5won 0 · lost 6

Claude Opus 5.5won 0 · lost 6

Muse Wonderwon 0 · lost 6

Gemini 4 Argonwon 0 · lost 6

§ 3 · Sources

Where the numbers come from

3 publications, 3 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-10-22

LMArena Text 1356

GDPval-AA ↗1 measureread 2026-10-22

GDPval-AA -195

Kagi LLM Benchmark ↗1 measureread 2026-10-22

Kagi LLM Benchmark 40.4%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=mistral-small-3-2)](https://publicai.io/model-index/m/mistral-small-3-2)