Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Mixtral 8x7b Instruct

Mistral

Strongest in Safe-prompt compliance (#62 of 82), weakest in Safety (#294 of 331). Above par in 2 of 12 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.1 and GPT-5 and ahead of Jamba 1.6 Mini and Zephyr 7B Beta.

§ 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.

Professional39.9#174/187
Medical33.8#139/149
Legal35#156/162
Human preference37.3#282/346
Human preference37.3#282/346
Safety43.9#294/331
Safe-prompt compliance47.7#62/82
Jailbreak resistance51.4#169/271
Toxicity avoidance52#179/271
Secure code42.8#204/273
Fairness44.1#214/296
Harm refusal39.8#285/296

§ 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 Mixtral 8x7b Instruct, left for the other.

Smollm2 1.7B Instructwon 7 · lost 1
DBRX Instructwon 7 · lost 2
Gemma 2B Itwon 6 · lost 2
Gemma 7B Itwon 6 · lost 2
Nous Hermes 2 Mixtral 8x7b Dpowon 6 · lost 2
DeepSeek LLM 67B Chatwon 6 · lost 3
Zephyr 7B Betawon 5 · lost 3
Jamba 1.6 Miniwon 5 · lost 4
Llama 3.2 1B Instructwon 4 · lost 4
Llama 3.2 3B Instructwon 4 · lost 4
Granite 3.1 2B Instructwon 4 · lost 4
Qwen1.5 14B Chatwon 4 · lost 4
Qwen3 30B A3B Instructwon 4 · lost 4
Mistral 7B Instruct V0.2won 3 · lost 5
Granite 3.0 2B Instructwon 3 · lost 5
Phi 3 Small 8k Instructwon 3 · lost 5
Starling Lm 7B Betawon 3 · lost 5
Granite 3.0 8B Instructwon 3 · lost 5
Command Rwon 3 · lost 5
Jamba 1.5 Miniwon 4 · lost 7
Grok 4.1 Fastwon 4 · lost 7
Jamba 1.6 Largewon 3 · lost 6
Command R Pluswon 4 · lost 8
Gemini 1.5 Flashwon 3 · lost 8
Grok 4.3won 3 · lost 8
Phi 3 Mini 128k Instructwon 2 · lost 6
Phi 3 Mini 4k Instructwon 2 · lost 6
Gemma 2 2B Itwon 2 · lost 6
Granite 3.1 8B Instructwon 2 · lost 6
Magistral Mediumwon 2 · lost 6
Qwen3 Vl 235B A22B Instructwon 2 · lost 6
Gemma 4 26B A4Bwon 2 · lost 6
GPT OSS 20Bwon 3 · lost 9
Llama 4 Scout Instructwon 3 · lost 9
GPT OSS 120Bwon 3 · lost 9
Grok 3won 3 · lost 9
Grok 4won 3 · lost 9
Ling 3.0 Flashwon 2 · lost 7
GPT-3.5 Turbowon 2 · lost 7
Llama 3 8B Instructwon 2 · lost 7
Claude 3 Haikuwon 2 · lost 7
Gemini 2.0 Flash Litewon 2 · lost 7
Gemma 2 9B Itwon 2 · lost 8
Mistral Largewon 2 · lost 8
Llama 3.3 70B Instructwon 2 · lost 8
Mistral Smallwon 2 · lost 8
DeepSeek V3.1won 2 · lost 8
Gemma 4 31Bwon 2 · lost 8
Llama 3.1 8B Instructwon 2 · lost 9
Jamba 1.5 Largewon 2 · lost 9
DeepSeek V3.2won 2 · lost 9
GLM-4.6won 2 · lost 9
NVIDIA Nemotron 3 Ultra 550B A55Bwon 2 · lost 9
DeepSeek V4 Flashwon 2 · lost 9
GPT-6 Lunawon 2 · lost 9
Mimo V2.6 Flashwon 2 · lost 9
GPT-6 Solwon 2 · lost 9
Llama 4 Maverick Instructwon 2 · lost 10
Gemini 1.5 Prowon 2 · lost 10
DeepSeek V3won 2 · lost 10
Gemini 2.5 Flashwon 2 · lost 10
Kimi K2won 2 · lost 10
DeepSeek R1won 2 · lost 10
Phi 3 Medium 4k Instructwon 1 · lost 7
Llama 3.1 Tulu 3 8Bwon 1 · lost 7
Nova Microwon 1 · lost 7
GPT-4won 1 · lost 7
Nova Prowon 1 · lost 7
Gemma 3 4B Itwon 1 · lost 7
QwQ 32Bwon 1 · lost 7
Mercury 2won 1 · lost 7
NVIDIA Nemotron 3 Super 120B A12Bwon 1 · lost 7
Qwen3.5 35B A3Bwon 1 · lost 7
Qwen3.5 27Bwon 1 · lost 7
Qwen3.5 122B A10Bwon 1 · lost 7
Qwen3.5 397B A17Bwon 1 · lost 7
Qwen 2.5 Instruct (7B)won 1 · lost 8
Claude 3 Sonnetwon 1 · lost 8
Claude 3 Opuswon 1 · lost 8
Claude 3.5 Haikuwon 1 · lost 9
Llama 3.1 70B Instructwon 1 · lost 10
Llama 3.1 405B Instructwon 1 · lost 10
Command Awon 1 · lost 10
GLM-4.5won 1 · lost 10
Mistral Large 4won 1 · lost 10
MiniMax M3won 1 · lost 10
Kimi K2.5won 1 · lost 10
GPT-5.6 Lunawon 1 · lost 10
Kimi K2.6won 1 · lost 10
DeepSeek V4 Prowon 1 · lost 10
Grok 4.5won 1 · lost 10
GPT-5.6 Terrawon 1 · lost 10
Mimo V2.5 Prowon 1 · lost 10
Qwen3.7 Maxwon 1 · lost 10
GLM-5.3 Flashwon 1 · lost 10
GPT-5.4won 1 · lost 10
GLM-5.2won 1 · lost 10
Gemini 3.5 Flashwon 1 · lost 10
GPT-5.5won 1 · lost 10
Qwen3.8 Maxwon 1 · lost 10
Gemini 3.6 Flashwon 1 · lost 10
GPT-5.6 Solwon 1 · lost 10
Gemini 3.8 Flashwon 1 · lost 10
GPT-4.1 Nanowon 1 · lost 11
Gemini 2.0 Flashwon 1 · lost 11
Claude 3.7 Sonnetwon 1 · lost 11
O4 Miniwon 1 · lost 11
GPT-4.1won 1 · lost 11
Qwen3 235B A22B Instructwon 1 · lost 11
O3won 1 · lost 11
Gemini 2.5 Prowon 1 · lost 11
Claude Sonnet 4.5won 1 · lost 11
C4ai Aya Expanse 8Bwon 0 · lost 8
Phi 4won 0 · lost 8
Nova Litewon 0 · lost 8
C4ai Aya Expanse 32Bwon 0 · lost 8
Mistral Small 24B Instructwon 0 · lost 8
Qwen Maxwon 0 · lost 8
Gemma 3 12B Itwon 0 · lost 8
MiniMax M2won 0 · lost 8
Gemma 3 27B Itwon 0 · lost 8
Hy3won 0 · lost 8
Kimi K2 Thinkingwon 0 · lost 9
Qwen2 72B Instructwon 0 · lost 9
Llama 3 70B Instructwon 0 · lost 9
Grok 3 Miniwon 0 · lost 9
Gemini 2.5 Flash Litewon 0 · lost 9
Claude Sonnet 4.6won 0 · lost 9
Gemini 3 Prowon 0 · lost 9
Claude Opus 4.6won 0 · lost 9
Gemma 2 27B Itwon 0 · lost 10
Mixtral 8x22b Instructwon 0 · lost 11
GPT-4o Miniwon 0 · lost 11
O1 Miniwon 0 · lost 11
Claude 3.5 Sonnetwon 0 · lost 11
MiniMax M2.7won 0 · lost 11
GPT-5.2won 0 · lost 11
Inklingwon 0 · lost 11
Grok 4.7won 0 · lost 11
Grok 4.6won 0 · lost 11
Claude Sonnet 5won 0 · lost 11
GLM-5.1won 0 · lost 11
Mimo V2.6 Prowon 0 · lost 11
Claude Opus 4.8won 0 · lost 11
Claude Opus 5won 0 · lost 11
Muse Spark 1.1won 0 · lost 11
Claude Opus 4.7won 0 · lost 11
Claude Opus 5.5won 0 · lost 11
Qwen2.5 72B Instructwon 0 · lost 12
GPT-4 Turbowon 0 · lost 12
GPT-4owon 0 · lost 12
GPT-5 Nanowon 0 · lost 12
O3 Miniwon 0 · lost 12
GPT-4.1 Miniwon 0 · lost 12
GPT-5 Miniwon 0 · lost 12
O1won 0 · lost 12
Claude Sonnet 4won 0 · lost 12
Claude Haiku 4.5won 0 · lost 12
Claude Opus 4won 0 · lost 12
GPT-5won 0 · lost 12
GPT-5.1won 0 · lost 12

§ 3 · Sources

Where the numbers come from

4 publications, 14 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-10-19
LMArena Text 1197
Vals.ai ↗2 measuresread 2026-10-19
Vals · LegalBench 55.84%Vals · MedQA 53.22%
HELM Safety ↗5 measuresread 2026-10-19
HELM Safety · HarmBench 45.1%HELM Safety · SimpleSafetyTests 90.5%HELM Safety · Anthropic Red Team 92.8%HELM Safety · BBQ 85.7%HELM Safety · XSTest 93.1%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-10-19
Enkrypt · Jailbreak risk 11.6%Enkrypt · Harmful content risk 61.7%Enkrypt · CBRN risk 13.3%Enkrypt · Toxicity risk 4.8%Enkrypt · Bias risk 88.6%Enkrypt · Insecure code risk 48%

Badge

PublicAI Index badge for Mixtral 8x7b Instruct[![PublicAI Index](https://publicai.io/model-index/badge?model=mixtral-8x7b-instruct)](https://publicai.io/model-index/m/mixtral-8x7b-instruct)