The LLM benchmark aggregator.

Mistral Small 3 24B Instruct

Mistral · 24B · open weights

Strongest in Factual grounding (#11 of 104), weakest in Harm refusal (#252 of 292). Above par in 4 of 10 scopes. Among the models it meets almost everywhere, it finishes behind O1 and Claude 3.5 Sonnet and ahead of Kimi K2.5 and Grok 4.1 Fast.

§ 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.

Safety48.8−12.6#213/3293/3

Factual grounding62.3−8.4#11/1041/1

Safe-prompt compliance52.6−7.8#48/821/1

Fairness49.6−20.4#118/2922/2

Toxicity avoidance53.9−5.1#129/2681/1

Jailbreak resistance53.8−11.2#131/2681/1

Secure code43.8−22.4#199/2701/1

Harm refusal44.1−17.4#252/2922/2

Human preference44.6−24.2#252/3541/1

§ 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 24B Instruct, left for the other.

H2o Danube3 500M Chatwon 6 · lost 0

Qwen2.5 0.5B Instructwon 6 · lost 0

Magistral Smallwon 6 · lost 0

Magistral Small 1.2won 6 · lost 0

Falcon H1 0.5B Instructwon 6 · lost 0

Command Rwon 6 · lost 0

OLMoE 1B-7B Instructwon 7 · lost 0

Mistral Instruct v0.1 (7B)won 7 · lost 0

Jamba Mini 1.7won 7 · lost 0

OLMo 7B Instructwon 8 · lost 0

Zephyr 7B Betawon 8 · lost 0

Nous Hermes 2 Mixtral 8x7B DPOwon 8 · lost 0

Mixtral 8x7B Instructwon 9 · lost 0

DBRX Instructwon 8 · lost 1

Gemma 2B ITwon 7 · lost 1

SmolLM2 1.7B Instructwon 7 · lost 1

Gemma 7B ITwon 7 · lost 1

Gemma 2 9B ITwon 7 · lost 1

SmolLM 1.7B Instructwon 5 · lost 1

RakutenAI 7B Chatwon 5 · lost 1

PowerMoE 3Bwon 5 · lost 1

Phi 2won 5 · lost 1

PowerLM 3Bwon 5 · lost 1

Laguna Xs 2.1won 5 · lost 1

LFM2 350Mwon 5 · lost 1

RakutenAI 7B Instructwon 5 · lost 1

Grok Build 0.1won 5 · lost 1

Jamba 1.6 Miniwon 5 · lost 1

Command R7Bwon 5 · lost 1

SmolLM 360M Instructwon 5 · lost 1

Open Codestral Mambawon 5 · lost 1

DeepSeek LLM 67B Chatwon 7 · lost 2

GPT-3.5 Turbowon 7 · lost 2

Qwen1.5 14B Chatwon 6 · lost 2

Jamba 1.5 Miniwon 6 · lost 2

Mistral Instruct v0.3 (7B)won 5 · lost 2

Jamba Large 1.7won 5 · lost 2

Phi-4 Mini Instructwon 5 · lost 2

Falcon Mamba 7B Instructwon 4 · lost 2

GLM-4 9B Chatwon 4 · lost 2

SmolLM2 360M Instructwon 4 · lost 2

CodeLlama 7B Instructwon 4 · lost 2

Qwen2 7B Instructwon 4 · lost 2

Aya 23 8Bwon 4 · lost 2

Laguna S 2.1won 4 · lost 2

SEA LION V1 7B ITwon 4 · lost 2

DeepSeek R1 Distill Llama 8Bwon 4 · lost 2

H2o Danube3 4B Chatwon 4 · lost 2

LFM2 700Mwon 4 · lost 2

NexusRaven V2 13Bwon 4 · lost 2

Mimo V2.6 Pro Ultraspeedwon 4 · lost 2

Qwen2.5 3B Instructwon 4 · lost 2

Jamba 1.6 Largewon 4 · lost 2

Gemma 4 E2Bwon 4 · lost 2

Jamba Instructwon 4 · lost 2

Sarvam 1won 4 · lost 2

Qwen2.5 7B Instruct 1Mwon 4 · lost 2

DeepSeek Reasonerwon 4 · lost 2

Qwen2.5 1.5B Instructwon 4 · lost 2

Komodo 7B Basewon 4 · lost 2

Command Awon 6 · lost 3

GLM-4.6won 6 · lost 3

Mistral 7B Instruct v0.2won 5 · lost 3

Llama 3.2 3B Instructwon 5 · lost 3

Jamba 1.5 Largewon 5 · lost 3

Magistral Mediumwon 5 · lost 3

Command R+won 6 · lost 4

Grok 3won 6 · lost 4

OLMo 2 7B Instructwon 4 · lost 3

Qwen3 8Bwon 4 · lost 3

Mixtral 8x22B Instructwon 5 · lost 4

Amazon Nova Litewon 5 · lost 4

Llama 3.1 70B Instructwon 5 · lost 4

Grok 4won 5 · lost 4

Grok 4.1 Fastwon 5 · lost 4

Kimi K2.5won 5 · lost 4

DeepSeek R1 Distill Qwen 7Bwon 3 · lost 3

Ling 3.0 Flash VLwon 3 · lost 3

Ling 3.0 Flashwon 3 · lost 3

Granite 3.2 8B Instructwon 3 · lost 3

Aya 23 35Bwon 3 · lost 3

LFM2 1.2Bwon 3 · lost 3

Granite 3.0 1B A400M Instructwon 3 · lost 3

Yi 1.5 9B Chatwon 3 · lost 3

Gemma 4 E4Bwon 3 · lost 3

SeaLLMs V3 7B Chatwon 3 · lost 3

WizardLM 2.8x22Bwon 3 · lost 3

Hunyuan A13B Instructwon 3 · lost 3

Fuguwon 3 · lost 3

Qwen2.5 14B Instruct 1Mwon 3 · lost 3

GLM-5 Turbowon 3 · lost 3

EAI Llama 3.1 8B Instruct SageAlignwon 3 · lost 3

EAI SageAlign 8B LoRAwon 3 · lost 3

Qwen1.5 72B Chatwon 3 · lost 3

OLMo 2 32B Instructwon 3 · lost 3

Llama 3.2 1B Instructwon 4 · lost 4

Phi-3 Mini 128K Instructwon 4 · lost 4

Phi-3 Mini 4K Instructwon 4 · lost 4

Starling LM 7B Betawon 4 · lost 4

Granite 3.1 2B Instructwon 4 · lost 4

Gemma 2 2B ITwon 4 · lost 4

Granite 3.1 8B Instructwon 4 · lost 4

Qwen3 30B A3B Instructwon 4 · lost 4

NVIDIA Nemotron 3 Ultra 550B A55Bwon 4 · lost 4

DeepSeek V4 Flashwon 4 · lost 4

Grok 4.3won 4 · lost 4

Gemini 3.5 Flashwon 4 · lost 4

Gemini 3.6 Flashwon 4 · lost 4

DeepSeek R1won 5 · lost 5

Aya Expanse 8Bwon 4 · lost 5

Amazon Nova Microwon 4 · lost 5

Claude 3 Haikuwon 4 · lost 5

Aya Expanse 32Bwon 4 · lost 5

Gemma 3 4B ITwon 4 · lost 5

Gemini 1.5 Flashwon 4 · lost 5

Gemini 2.0 Flash-Litewon 4 · lost 5

DeepSeek V3.1won 4 · lost 5

Gemma 4 31Bwon 4 · lost 5

Kimi K2.6won 4 · lost 5

IBM Granite 4.0 Microwon 3 · lost 4

MiMo V2.6 Flashwon 3 · lost 4

GPT OSS 120Bwon 4 · lost 6

DeepSeek V3won 4 · lost 6

Llama 2 7B Chatwon 3 · lost 5

Llama 2 13B Chatwon 3 · lost 5

Granite 3.0 2B Instructwon 3 · lost 5

Llama 2 70B Chatwon 3 · lost 5

Phi-3 Small 8K Instructwon 3 · lost 5

Granite 3.0 8B Instructwon 3 · lost 5

Phi-3 Medium 4K Instructwon 3 · lost 5

Llama 3.1 8B Instructwon 3 · lost 5

Llama 3.1 Tulu 3 8Bwon 3 · lost 5

Amazon Nova Prowon 3 · lost 5

NVIDIA Nemotron 3 Super 120B A12Bwon 3 · lost 5

GLM-4.5won 3 · lost 5

MiniMax M3won 3 · lost 5

Qwen3.7 Maxwon 3 · lost 5

GLM-5.2won 3 · lost 5

Qwen3.8 Maxwon 3 · lost 5

Kimi K2.7 Codewon 2 · lost 4

Gemma 4 12Bwon 2 · lost 4

Granite 3.2 2B Instructwon 2 · lost 4

Gemma2 9B Cpt Sea Lionv3 Instructwon 2 · lost 4

Reflection Llama 3.1 70Bwon 2 · lost 4

Apertus 8B Instructwon 2 · lost 4

DeepSeek Chatwon 2 · lost 4

LongWriter Glm4 9Bwon 2 · lost 4

Granite 3.1 3B A800M Instructwon 2 · lost 4

Sarvam 30Bwon 2 · lost 4

GPT-5.6 Astrawon 2 · lost 4

Granite 4.0 H Microwon 2 · lost 4

K2 Chatwon 2 · lost 4

Krutrim 2 Instructwon 2 · lost 4

Internlm2 Chat 20Bwon 2 · lost 4

Fugu Ultra V2won 2 · lost 4

Llama 3 8B Instruct MopeyMulewon 2 · lost 4

Llama 3 8B Instructwon 3 · lost 6

Phi 4won 3 · lost 6

Granite 4.0 H Smallwon 3 · lost 6

GPT OSS 20Bwon 3 · lost 6

GPT-4.1 nanowon 3 · lost 6

Llama 3.1 405B Instructwon 3 · lost 6

Gemini 1.5 Prowon 3 · lost 6

GPT-4.1 miniwon 3 · lost 6

Qwen3.5 27Bwon 3 · lost 6

Qwen3.5 122B A10Bwon 3 · lost 6

DeepSeek V3.2won 3 · lost 6

Gemma 4 26B A4Bwon 3 · lost 6

GPT-6 Solwon 3 · lost 6

DeepSeek V4 Prowon 3 · lost 6

Llama 4 Scout Instructwon 3 · lost 7

Llama 4 Maverick Instructwon 3 · lost 7

Gemini 2.5 Flashwon 3 · lost 7

Kimi K2won 3 · lost 7

Qwen3 235B A22B Instructwon 3 · lost 7

Gemini 2.5 Prowon 3 · lost 7

Qwen 2.5 Instruct (7B)won 2 · lost 5

Claude Sonnet 4.6won 2 · lost 5

GPT-4won 2 · lost 6

QwQ 32Bwon 2 · lost 6

Qwen3 VL 235B A22B Instructwon 2 · lost 6

GPT-6 Lunawon 2 · lost 6

GLM-5.1won 2 · lost 6

Grok 4.5won 2 · lost 6

Qwen2 72B Instructwon 2 · lost 7

Llama 3.3 70B Instructwon 2 · lost 7

Mercury 2won 2 · lost 7

O3 Miniwon 2 · lost 7

Gemma 3 27B ITwon 2 · lost 7

Claude 3.7 Sonnetwon 2 · lost 7

Qwen3.5 35B A3Bwon 2 · lost 7

GPT-5.4won 2 · lost 7

GPT-5.5won 2 · lost 7

GPT-5.6 Solwon 2 · lost 7

GPT-5 miniwon 2 · lost 8

O4 Miniwon 2 · lost 8

Claude Haiku 4.5won 2 · lost 8

GPT-4.1won 2 · lost 8

GPT-5.1won 2 · lost 8

Claude Sonnet 4.5won 2 · lost 8

Granite 3.0 3B A800M Instructwon 1 · lost 5

Dolphin 2.5 Mixtral 8x7bwon 1 · lost 5

Qwen2.5 32B Instructwon 1 · lost 5

Qwen2 VL 72Bwon 1 · lost 5

Qwen2.5 14B Instructwon 1 · lost 5

Phi 3 Medium 128k Instructwon 1 · lost 5

Qwen2 57B A14B Instructwon 1 · lost 5

Smaug Llama 3 70B Instructwon 1 · lost 5

Phi 3 Small 128k Instructwon 1 · lost 5

GPT OSS Safeguard 20Bwon 1 · lost 5

Kimi K2 Thinkingwon 1 · lost 5

SeaLLM 7B V2won 1 · lost 5

Apertus 70B Instructwon 1 · lost 5

Phi 3.5 Mini Instructwon 1 · lost 5

Llama 3.1 Tulu 3 8B SFTwon 1 · lost 5

Llama 3.1 Tulu 3 8B DPOwon 1 · lost 5

Phi 3.5 MoE Instructwon 1 · lost 5

Llama 3.2 Vision (11B)won 1 · lost 5

Titan Text Express V1won 1 · lost 5

Llama 3 8B Instruct RRwon 1 · lost 5

Nova Premierwon 1 · lost 5

Sarvam 105Bwon 1 · lost 5

Llama 3.2 Vision (90B)won 1 · lost 5

Meta SecAlign 8Bwon 1 · lost 5

GPT-4.5won 1 · lost 5

Qwen3 Next 80B A3B Thinkingwon 1 · lost 6

GLM-4.5 Airwon 1 · lost 6

GPT-5.6 Lunawon 1 · lost 6

Gemini 3 Prowon 1 · lost 6

Gemini 3.8 Flashwon 1 · lost 6

Claude Opus 4.6won 1 · lost 6

Llama 3.1 Nemotron 70B Instructwon 1 · lost 7

Qwen Maxwon 1 · lost 7

Claude 3.5 Haikuwon 1 · lost 7

Gemini 2.0 Flashwon 1 · lost 7

Mistral Large 4won 1 · lost 7

Qwen3.5 397B A17Bwon 1 · lost 7

MiMo V2.5 Prowon 1 · lost 7

GPT-5.6 Terrawon 1 · lost 7

GLM-5.3 Flashwon 1 · lost 7

MiMo V2.6 Prowon 1 · lost 7

Claude Opus 5won 1 · lost 7

Muse Spark 1.1won 1 · lost 7

Claude 3 Sonnetwon 1 · lost 8

GPT-4o miniwon 1 · lost 8

Claude 3 Opuswon 1 · lost 8

Gemma 3 12B ITwon 1 · lost 8

MiniMax M2.7won 1 · lost 8

O3won 1 · lost 8

GPT-5.2won 1 · lost 8

Claude Opus 4.7won 1 · lost 8

Claude Opus 5.5won 1 · lost 8

GPT-4owon 1 · lost 9

GPT-5 nanowon 1 · lost 9

Claude Sonnet 4won 1 · lost 9

Claude Opus 4won 1 · lost 9

GPT-5won 1 · lost 9

Foundation Sec 8B Instructwon 0 · lost 6

Apriel 1.5 15B Thinkerwon 0 · lost 6

Mistral NeMo Minitron 8B Instructwon 0 · lost 6

Grok 3 Miniwon 0 · lost 6

Gemini 2.5 Flash-Litewon 0 · lost 7

Llama 3 70B Instructwon 0 · lost 8

Gemma 2 27B ITwon 0 · lost 8

MiniMax M2won 0 · lost 8

Grok 4.7won 0 · lost 8

Inklingwon 0 · lost 8

Hy3won 0 · lost 8

Grok 4.6won 0 · lost 8

Claude Sonnet 5won 0 · lost 8

Claude Opus 4.8won 0 · lost 8

Qwen2.5 72B Instructwon 0 · lost 9

GPT-4 Turbowon 0 · lost 9

O1 Miniwon 0 · lost 9

Claude 3.5 Sonnetwon 0 · lost 9

O1won 0 · lost 9

§ 3 · Sources

Where the numbers come from

4 publications, 13 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-10

LMArena Text 1274

HELM Safety ↗5 measuresread 2026-11-10

HELM Safety · HarmBench 45.2%HELM Safety · SimpleSafetyTests 93.3%HELM Safety · Anthropic Red Team 96.4%HELM Safety · BBQ 93.3%HELM Safety · XSTest 95.3%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-10

Enkrypt · Jailbreak risk 9.6%Enkrypt · Harmful content risk 54.4%Enkrypt · CBRN risk 9.3%Enkrypt · Toxicity risk 3.5%Enkrypt · Bias risk 84.8%Enkrypt · Insecure code risk 45.8%

Vectara Hallucination Leaderboard ↗1 measureread 2026-11-10

Vectara · Factual consistency 94.9%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=mistral-small-3-24b-instruct)](https://publicai.io/model-index/m/mistral-small-3-24b-instruct)