priorsBuilder

Mistral · released 2025-05-21

Devstral Small

Measured on 15 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. #529none of 5874.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #380none of 526-50.8

Leader: Opus 5.5 · 46.4

All 15 benchmarks

show 13 more

agentic

τ²-Bench Telecom

393 results
  1. #227none of 39338.0%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #205none of 28225.8%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #257none of 3876.1%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #415none of 6108.7

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #301none of 39934.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #381none of 52615.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #253none of 52623.1%

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

knowledge

GPQA Diamond

539 results
  1. #440none of 53943.4%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #213none of 28563.2%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #371none of 52332.0%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #159none of 22829.3%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #121none of 16268.4%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #409none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%