priorsBuilder

Mistral · released 2025-05-07

Mistral Medium 3

Measured on 22 benchmarks.

General frontier

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

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #527none of 5874.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #277none of 526-31.4

Leader: Opus 5.5 · 46.4

All 22 benchmarks

show 20 more

agentic

τ²-Bench Telecom

393 results
  1. #296none of 39324.3%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #153none of 28240.0%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #285none of 3873.8%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #397none of 6109.0

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #262none of 39939.3%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #324none of 52618.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #160none of 52639.1%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

GPQA Diamond

539 results
  1. #374none of 53957.8%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #140none of 28576.0%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU-Pro

265 results
  1. #218none of 26553.0%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #374none of 52331.3%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #156none of 22830.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #56none of 16290.7%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #398none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #54none of 1710.7%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #80none of 18199.7%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #149none of 3511.9s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #307none of 35145.1

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #16none of 1770.5s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #26none of 176106.0

Leader: Muse Spark 1.1 · 204.3