priorsBuilder

Mistral · released 2026-10-06

Mistral Large 4

Measured on 44 benchmarks.

General frontier

35.3

#70 of 136 models

includes estimates: 24% of the mix is measured for this model

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #117default of 58735.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #161default of 526-5.3

Leader: Opus 5.5 · 46.4

All 44 benchmarks

show 42 more

agentic

AA-Briefcase v1.1

224 results
  1. #56default of 2241394

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #42high of 50-6.6%

Leader: Opus 5.5 · 15.5%

agentic

AutomationBench-AA

219 results
  1. #35default of 21959.9%

Leader: Gemini 4 · 77.5%

agentic

BioMysteryBench

27 results
  1. #20high of 2767.0%

Leader: Sonnet 5.5 · 81.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #9high of 7915.8%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #42high of 7831.7%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #25high of 6930.4%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 4.0 (Vals)

47 results
  1. #23high of 4722.7%

Leader: Opus 5.5 · 65.2%

coding

Arena WebDev

122 results
  1. #40high of 1221541

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #41high of 7730.6%

Leader: Sonnet 5.5 · 69.8%

coding

IOI

44 results
  1. #31high of 4445.3%

Leader: Gemini 4 · 100.0%

coding

SciCode

226 results
  1. #65default of 22654.2%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v4-AA

216 results
  1. #48default of 21626.8%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench 1-100

22 results
  1. #17high of 2214.3%

Leader: Opus 5.5 · 30.4%

coding

Vibe Code Bench v1.1

105 results
  1. #28high of 10578.4%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #72default of 61038.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #95high of 2201429

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #99high of 2201425

Leader: Gemini 4 · 1553

composite

Vals Index

47 results
  1. #35high of 4748.0%

Leader: Gemini 4 · 68.9%

cost

AA Intelligence Index Cost per Task

177 results
  1. #122default of 177$1.13

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #124default of 177$1,607

Leader: GPT-6 Luna · $10.63

creative

threejseval

34 results
  1. #34high of 341070

Leader: Opus 5.5 · 2079

economics

Excel Modeling Benchmark

74 results
  1. #46high of 7456.2%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #24high of 7854.7%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #69default of 21018.6%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #66default of 2881423

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #214default of 52625.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #81default of 52658.1%

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

knowledge

Harvey LAB-AA v1.1

27 results
  1. #12default of 273.1%

Leader: Muse Wonder Full (Max) · 13.1%

knowledge

MedCode

94 results
  1. #57high of 9440.7%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #52high of 9680.4%

Leader: Opus 5.5 · 91.4%

knowledge

MMMU-Pro

265 results
  1. #84default of 26576.4%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #56default of 52381.3%

Leader: Kimi K3 · 88.7%

math

ProofBench v1.1

52 results
  1. #47high of 5210.0%

Leader: Sonnet 5.5 · 100.0%

reasoning

CritPt

529 results
  1. #111default of 52910.6%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

MysteryMechanism

27 results
  1. #27high of 2712.2%

Leader: GPT-6 Astra · 53.2%

reasoning

Roboflow Visual Reasoning

102 results
  1. #70high of 10257.6%
  2. #92low of 10238.9%

Leader: GPT-6 Astra · 91.2%

reliability

Tool-call error rate

171 results
  1. #166high of 17110.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #96high of 18199.4%

Leader: GPT-5 Pro · 100.0%

safety

CWE-Bench

19 results
  1. #15default of 1950.8%

Leader: Grok 4.7 · 68.3%

speed

Provider latency

177 results
  1. #84high of 1771.2s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #85high of 17667.0

Leader: Muse Spark 1.1 · 204.3