Request a Pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Magistral Small

Mistral

Strongest in Reasoning (#112 of 147, on 1 of its 3 boards), weakest in Safety (#294 of 327). Above par in 0 of 10 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.5 and Claude Opus 5.5 and ahead of Jamba 1.6 Mini and Command R+.

§ 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.

Reasoning45.5#136/195
Reasoning41.9#112/147
Core abilities37.8#197/200
General intelligence32.4#180/180
Safety43.2#294/327
Fairness45.4#181/290
Secure code42.7#200/268
Jailbreak resistance42.7#205/266
Toxicity avoidance46.7#215/266
Harm refusal40#278/290

§ 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, left for the other.

OLMoE 1B-7B Instructwon 6 · lost 0
OLMo 7B Instructwon 5 · lost 1
SmolLM 1.7B Instructwon 5 · lost 1
PowerMoE 3Bwon 5 · lost 1
RakutenAI 7B Instructwon 5 · lost 1
Mistral Instruct v0.1 (7B)won 4 · lost 2
RakutenAI 7B Chatwon 4 · lost 2
DBRX Instructwon 4 · lost 2
Phi 2won 4 · lost 2
Gemma 7B ITwon 4 · lost 2
H2o Danube3 500M Chatwon 4 · lost 2
PowerLM 3Bwon 4 · lost 2
SmolLM2 1.7B Instructwon 4 · lost 2
Qwen3 30B A3B Instructwon 4 · lost 2
Laguna Xs 2.1won 4 · lost 2
LFM2 350Mwon 4 · lost 2
Falcon Mamba 7B Instructwon 4 · lost 2
Nous Hermes 2 Mixtral 8x7B DPOwon 4 · lost 2
SmolLM2 360M Instructwon 4 · lost 2
CodeLlama 7B Instructwon 4 · lost 2
Command R+won 5 · lost 3
Jamba 1.6 Miniwon 4 · lost 3
GLM-4 9B Chatwon 3 · lost 3
Mistral Instruct v0.3 (7B)won 3 · lost 3
Qwen2.5 0.5B Instructwon 3 · lost 3
Qwen2 7B Instructwon 3 · lost 3
Gemma 2B ITwon 3 · lost 3
Aya 23 8Bwon 3 · lost 3
Jamba 1.5 Largewon 3 · lost 3
Llama 3.3 70B Instructwon 4 · lost 4
GPT-3.5 Turbowon 4 · lost 4
Grok 4.1 Fastwon 4 · lost 4
Gemma 4 31Bwon 5 · lost 5
Grok 3won 5 · lost 5
Kimi K2won 4 · lost 6
DeepSeek V3won 4 · lost 6
Gemini 1.5 Prowon 3 · lost 5
Llama 3.1 405B Instructwon 3 · lost 5
Grok 4.3won 3 · lost 5
Grok Build 0.1won 3 · lost 5
Laguna S 2.1won 2 · lost 4
SEA LION V1 7B ITwon 2 · lost 4
Qwen1.5 14B Chatwon 2 · lost 4
DeepSeek R1 Distill Qwen 7Bwon 2 · lost 4
DeepSeek R1 Distill Llama 8Bwon 2 · lost 4
H2o Danube3 4B Chatwon 2 · lost 4
Ling 3.0 Flash VLwon 2 · lost 4
NexusRaven V2 13Bwon 2 · lost 4
SmolLM 360M Instructwon 2 · lost 4
Gemma 2 9B ITwon 2 · lost 4
Qwen3 8Bwon 2 · lost 4
Granite 3.2 8B Instructwon 2 · lost 4
Mistral 7B Instruct v0.2won 2 · lost 4
Jamba 1.5 Miniwon 2 · lost 4
NVIDIA Nemotron 3 Super 120B A12Bwon 2 · lost 4
Gemma 4 E2Bwon 2 · lost 4
Yi 1.5 9B Chatwon 2 · lost 4
Gemma 4 E4Bwon 2 · lost 4
Komodo 7B Basewon 2 · lost 4
Gemma 2 2B ITwon 2 · lost 4
WizardLM 2.8x22Bwon 2 · lost 4
Granite 3.1 2B Instructwon 2 · lost 4
Llama 3.2 3B Instructwon 2 · lost 4
IBM Granite 4.0 Microwon 2 · lost 4
Gemma 4 12Bwon 2 · lost 4
Granite 3.2 2B Instructwon 2 · lost 4
Llama 3.2 1B Instructwon 2 · lost 4
Gemma 4 26B A4Bwon 2 · lost 4
Granite 3.1 3B A800M Instructwon 2 · lost 4
Granite 3.1 8B Instructwon 2 · lost 4
Llama 4 Maverick Instructwon 3 · lost 7
Gemini 2.5 Flashwon 3 · lost 7
Claude 3.5 Haikuwon 2 · lost 5
Gemini 1.5 Flashwon 2 · lost 5
Magistral Small 1.2won 2 · lost 5
Ling 3.0 Flashwon 2 · lost 5
GPT-4owon 2 · lost 6
O1 Miniwon 2 · lost 6
Claude 3 Opuswon 2 · lost 6
GPT-4 Turbowon 2 · lost 6
Claude 3.7 Sonnetwon 2 · lost 6
Jamba Mini 1.7won 2 · lost 6
Command Awon 2 · lost 7
Kimi K2.7 Codewon 2 · lost 7
Llama 4 Scout Instructwon 2 · lost 7
GLM-4.6won 2 · lost 7
DeepSeek V4 Flashwon 2 · lost 7
GPT OSS 20Bwon 2 · lost 7
MiMo V2.6 Flashwon 2 · lost 7
GPT-4o miniwon 2 · lost 8
MiniMax M3won 2 · lost 8
Gemini 2.0 Flashwon 2 · lost 8
GLM-5.3 Flashwon 2 · lost 8
GPT OSS 120Bwon 2 · lost 8
NVIDIA Nemotron 3 Ultra 550B A55Bwon 2 · lost 8
GLM-5.2won 2 · lost 8
GPT-4.1won 2 · lost 8
Qwen3 235B A22B Instructwon 2 · lost 8
MiniMax M2won 2 · lost 8
DeepSeek R1won 2 · lost 8
Grok 4won 2 · lost 8
OLMo 2 7B Instructwon 1 · lost 5
Falcon H1 0.5B Instructwon 1 · lost 5
Zephyr 7B Betawon 1 · lost 5
Llama 3.1 70B Instructwon 1 · lost 5
Command R7Bwon 1 · lost 5
LFM2 700Mwon 1 · lost 5
DeepSeek LLM 67B Chatwon 1 · lost 5
Mimo V2.6 Pro Ultraspeedwon 1 · lost 5
Phi-4 Mini Instructwon 1 · lost 5
Open Codestral Mambawon 1 · lost 5
Qwen2.5 3B Instructwon 1 · lost 5
Aya 23 35Bwon 1 · lost 5
LFM2 1.2Bwon 1 · lost 5
Granite 3.0 1B A400M Instructwon 1 · lost 5
QwQ 32Bwon 1 · lost 5
Jamba Instructwon 1 · lost 5
Sarvam 1won 1 · lost 5
Qwen2.5 7B Instruct 1Mwon 1 · lost 5
SeaLLMs V3 7B Chatwon 1 · lost 5
Qwen2.5 1.5B Instructwon 1 · lost 5
Fuguwon 1 · lost 5
Gemini 2.0 Flash-Litewon 1 · lost 5
Granite 3.0 3B A800M Instructwon 1 · lost 5
Llama 3.1 8B Instructwon 1 · lost 5
Dolphin 2.5 Mixtral 8x7bwon 1 · lost 5
Granite 3.0 2B Instructwon 1 · lost 5
Mercury 2won 1 · lost 5
Gemma2 9B Cpt Sea Lionv3 Instructwon 1 · lost 5
Reflection Llama 3.1 70Bwon 1 · lost 5
Qwen2.5 32B Instructwon 1 · lost 5
LongWriter Glm4 9Bwon 1 · lost 5
Qwen2 VL 72Bwon 1 · lost 5
GLM-5 Turbowon 1 · lost 5
Phi-3 Medium 4K Instructwon 1 · lost 5
Sarvam 30Bwon 1 · lost 5
Qwen2.5 14B Instructwon 1 · lost 5
Phi 3 Medium 128k Instructwon 1 · lost 5
Smaug Llama 3 70B Instructwon 1 · lost 5
Phi 3 Small 128k Instructwon 1 · lost 5
Granite 3.0 8B Instructwon 1 · lost 5
Llama 3 8B Instructwon 1 · lost 5
EAI Llama 3.1 8B Instruct SageAlignwon 1 · lost 5
Gemma 3 12B ITwon 1 · lost 5
SeaLLM 7B V2won 1 · lost 5
Granite 4.0 H Microwon 1 · lost 5
Phi-3 Small 8K Instructwon 1 · lost 5
Phi-3 Mini 128K Instructwon 1 · lost 5
Phi 3.5 Mini Instructwon 1 · lost 5
K2 Chatwon 1 · lost 5
Llama 3.1 Tulu 3 8B SFTwon 1 · lost 5
Phi-3 Mini 4K Instructwon 1 · lost 5
Amazon Nova Prowon 1 · lost 5
Llama 3.1 Tulu 3 8B DPOwon 1 · lost 5
Krutrim 2 Instructwon 1 · lost 5
Llama 3.1 Tulu 3 8Bwon 1 · lost 5
Amazon Nova Microwon 1 · lost 5
Llama 3.2 Vision (11B)won 1 · lost 5
Titan Text Express V1won 1 · lost 5
Llama 3.1 Nemotron 70B Instructwon 1 · lost 5
Llama 2 13B Chatwon 1 · lost 5
Llama 2 70B Chatwon 1 · lost 5
Sarvam 105Bwon 1 · lost 5
Llama 3.2 Vision (90B)won 1 · lost 5
Jamba 1.6 Largewon 1 · lost 6
MiMo V2.5 Prowon 1 · lost 6
Claude 3.5 Sonnetwon 1 · lost 7
O3 Miniwon 1 · lost 7
Claude 3 Haikuwon 1 · lost 7
Kimi K2.6won 1 · lost 7
GPT-4.1 nanowon 1 · lost 8
GPT-4.1 miniwon 1 · lost 8
GPT-6 Solwon 1 · lost 8
Qwen3.7 Maxwon 1 · lost 8
Gemini 3.6 Flashwon 1 · lost 8
Gemini 3.5 Flashwon 1 · lost 8
Mistral Large 4won 1 · lost 9
DeepSeek V3.2won 1 · lost 9
DeepSeek V3.1won 1 · lost 9
MiMo V2.6 Prowon 1 · lost 9
DeepSeek V4 Prowon 1 · lost 9
Claude Sonnet 4.5won 1 · lost 9
GPT-5.4won 1 · lost 9
Gemini 2.5 Prowon 1 · lost 9
GPT-5.6 Solwon 1 · lost 9
Kimi K2.5won 1 · lost 9
Mixtral 8x22B Instructwon 0 · lost 6
Mistral Small 3 24B Instructwon 0 · lost 6
Hunyuan A13B Instructwon 0 · lost 6
Starling LM 7B Betawon 0 · lost 6
Apertus 8B Instructwon 0 · lost 6
Qwen2.5 14B Instruct 1Mwon 0 · lost 6
Qwen 2.5 Instruct (7B)won 0 · lost 6
Qwen3 VL 235B A22B Instructwon 0 · lost 6
Qwen2 57B A14B Instructwon 0 · lost 6
GPT-5.6 Astrawon 0 · lost 6
GPT OSS Safeguard 20Bwon 0 · lost 6
Apertus 70B Instructwon 0 · lost 6
EAI SageAlign 8B LoRAwon 0 · lost 6
Qwen3.5 35B A3Bwon 0 · lost 6
Qwen Maxwon 0 · lost 6
Qwen3.5 27Bwon 0 · lost 6
GPT-4won 0 · lost 6
Qwen3.5 122B A10Bwon 0 · lost 6
Aya Expanse 32Bwon 0 · lost 6
Internlm2 Chat 20Bwon 0 · lost 6
Llama 3 8B Instruct RRwon 0 · lost 6
Fugu Ultra V2won 0 · lost 6
Granite 4.0 H Smallwon 0 · lost 6
Llama 2 7B Chatwon 0 · lost 6
Qwen2 72B Instructwon 0 · lost 6
Llama 3 8B Instruct MopeyMulewon 0 · lost 6
Claude 3 Sonnetwon 0 · lost 6
Cogito 671B V2 P1won 0 · lost 6
Qwen2.5 72B Instructwon 0 · lost 6
Foundation Sec 8B Instructwon 0 · lost 6
Gemma 2 27B ITwon 0 · lost 6
Meta SecAlign 8Bwon 0 · lost 6
Apriel 1.5 15B Thinkerwon 0 · lost 6
Mistral NeMo Minitron 8B Instructwon 0 · lost 6
Phi 4won 0 · lost 6
Hy3won 0 · lost 6
Gemini 2.5 Flash-Litewon 0 · lost 6
MiniMax M2.7won 0 · lost 7
Claude Sonnet 4.6won 0 · lost 7
Grok 3 Miniwon 0 · lost 7
Gemini 3 Prowon 0 · lost 7
O1won 0 · lost 8
Claude Haiku 4.5won 0 · lost 8
GPT-5.1won 0 · lost 8
GLM-5.1won 0 · lost 8
Magistral Mediumwon 0 · lost 8
Gemma 3 4B ITwon 0 · lost 8
Jamba Large 1.7won 0 · lost 8
Llama 3 70B Instructwon 0 · lost 8
Gemma 3 27B ITwon 0 · lost 8
Nova Premierwon 0 · lost 8
Muse Spark 1.1won 0 · lost 8
Claude Opus 4.6won 0 · lost 8
Qwen3.5 397B A17Bwon 0 · lost 8
Claude Sonnet 5won 0 · lost 9
GLM-4.5won 0 · lost 9
Claude Opus 5won 0 · lost 9
GPT-5.6 Lunawon 0 · lost 10
GPT-6 Lunawon 0 · lost 10
Inklingwon 0 · lost 10
GPT-5.2won 0 · lost 10
GPT-5.6 Terrawon 0 · lost 10
Gemini 3.8 Flashwon 0 · lost 10
GPT-5 nanowon 0 · lost 10
Grok 4.6won 0 · lost 10
Kimi K2 Thinkingwon 0 · lost 10
Qwen3.8 Maxwon 0 · lost 10
Claude Opus 4.7won 0 · lost 10
O4 Miniwon 0 · lost 10
O3won 0 · lost 10
Grok 4.7won 0 · lost 10
GPT-5 miniwon 0 · lost 10
GPT-5won 0 · lost 10
Claude Sonnet 4won 0 · lost 10
Claude Opus 4won 0 · lost 10
Grok 4.5won 0 · lost 10
Claude Opus 4.8won 0 · lost 10
Claude Opus 5.5won 0 · lost 10
GPT-5.5won 0 · lost 10

§ 3 · Sources

Where the numbers come from

3 publications, 8 figures. Every one links to the page it was read from.

ARC-AGI-2 ↗1 measureread 2026-11-11
ARC-AGI-2 0%
Kagi LLM Benchmark ↗1 measureread 2026-11-11
Kagi LLM Benchmark 6.3%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-11
Enkrypt · Jailbreak risk 19%Enkrypt · Harmful content risk 66.7%Enkrypt · CBRN risk 23.8%Enkrypt · Toxicity risk 8.4%Enkrypt · Bias risk 85%Enkrypt · Insecure code risk 48%

Badge

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