priorsBuilder

Mistral · released 2025-12-09

Devstral 2

Measured on 30 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. #565none of 5873.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #349none of 526-46.7

Leader: Opus 5.5 · 46.4

All 30 benchmarks

show 28 more

agentic

AA-Briefcase v1.1

224 results
  1. #176none of 224482

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #169none of 2193.1%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #291none of 39324.9%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #142none of 20610.5%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena WebDev

122 results
  1. #119none of 1221197

Leader: Opus 5.5 · 1813

coding

LiveCodeBench

282 results
  1. #141none of 28244.8%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #105none of 12751.8%

Leader: Fable 5.1 · 90.5%

coding

SciCode

226 results
  1. #198none of 22632.8%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #73none of 8562.8%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench Hard-AA

387 results
  1. #171none of 38718.9%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #155none of 23830.3%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #200none of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #419none of 6108.6

Leader: Opus 5.5 · 57.6

economics

GDP.pdf

210 results
  1. #182none of 2102.4%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #210none of 288544

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #272none of 39938.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #283none of 52620.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #333none of 52614.7%

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

knowledge

Global-MMLU-Lite

118 results
  1. #84none of 11877.5%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #363none of 53959.4%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #137none of 28576.2%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #367none of 52332.3%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #144none of 22836.7%

Leader: GPT-5.2 · 99.0%

reasoning

CritPt

529 results
  1. #411none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #60none of 1710.8%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #49none of 18199.9%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

177 results
  1. #53none of 1770.9s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #41none of 17690.0

Leader: Muse Spark 1.1 · 204.3