priorsBuilder

Mistral · released 2025-01-30

Mistral Small 3

Measured on 15 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. #546none of 5873.8%

Leader: Opus 5.5 · 61.4%

All 15 benchmarks

show 14 more

agentic

τ²-Bench Telecom

393 results
  1. #325none of 39319.6%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #206none of 28225.2%

Leader: Gemini 3 Pro · 91.7%

composite

AA Intelligence Index v4.3.2

610 results
  1. #491none of 6106.7

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #362none of 39926.4%

Leader: Grok 4.3 · 83.3%

knowledge

GPQA Diamond

539 results
  1. #432none of 53946.2%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #204none of 28565.2%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #486none of 5230.0%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #212none of 2284.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #111none of 16271.5%

Leader: GPT-5 · 99.4%

reliability

Uptime (7d)

181 results
  1. #14none of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #53none of 3510.9s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #283none of 35155.4

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #5none of 1770.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #116none of 17651.0

Leader: Muse Spark 1.1 · 204.3