Back

Mistral

Mixtral 8x7B Instruct

Open weightsHugging Face
Intelligence
5.1
Rank 708 of 744 measured models
Output speed
25.5 t/s
Rank 395 of 403 measured models
Price/1M
$0.512
Rank 280 of 659 measured models
Context window
33K
Rank 1012 of 1199 measured models

Mixtral 8x7B Instruct scores 5.1 on the Artificial Analysis Intelligence Index, ranking 708th of 744 measured models. The closest models on this index are Apertus 70B Instruct (5.1), DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) (5.1), and Gemma 3 270M (5.1). At $0.512 per million tokens (3:1 input/output blended price), it is cheaper than Apertus 70B Instruct ($1.35).

Artificial Analysis Indices
Intelligence5.1
Rank 708 of 744 measured models
Standard Benchmarks
MMLU Pro38.7%
Rank 326 of 349 measured models
GPQA Diamond29.2%
Rank 585 of 619 measured models
HLE4.7%
Rank 504 of 664 measured models
LiveCodeBench6.6%
Rank 329 of 343 measured models
MATH-50029.9%
Rank 192 of 202 measured models
AIME 20240.0%
Rank 181 of 194 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy