priorsBuilder

Mistral · released 2023-12-11

Mixtral 8x7B Instruct

Measured on 10 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

1 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #470none of 5874.7%

Leader: Opus 5.5 · 61.4%

All 10 benchmarks

show 9 more

coding

LiveCodeBench

282 results
  1. #269none of 2826.6%

Leader: Gemini 3 Pro · 91.7%

composite

AA Intelligence Index v4.3.2

610 results
  1. #579none of 6105.1

Leader: Opus 5.5 · 57.6

knowledge

GPQA Diamond

539 results
  1. #508none of 53929.2%

Leader: GPT-6 Astra · 96.3%

knowledge

MedQA (Vals)

80 results
  1. #75none of 8053.2%

Leader: o1 · 96.5%

knowledge

MMLU-Pro

285 results
  1. #265none of 28538.7%

Leader: Gemini 3 Pro · 89.8%

math

MATH-500

162 results
  1. #154none of 16229.9%

Leader: GPT-5 · 99.4%

reasoning

LegalBench

135 results
  1. #128none of 13555.8%

Leader: Fable 5 · 88.6%

speed

Latency (Time to First Token)

351 results
  1. #91none of 3511.1s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #346none of 35125.0

Leader: Celeris-1 · 1522.5