priorsBuilder

Mistral · released 2026-03-16

Mistral Small 4

Measured on 31 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. #316default of 5879.9%
  2. #542none of 5873.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #274default of 526-30.4
  2. #361none of 526-48.5

Leader: Opus 5.5 · 46.4

All 31 benchmarks

show 29 more

agentic

AA-AnalystAgent

44 results
  1. #44default of 441.3%

Leader: Gemini 3.7 Flash · 60.0%

agentic

AA-Briefcase v1.1

224 results
  1. #195default of 224241

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #192default of 2191.0%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #222default of 39341.2%
  2. #330none of 39318.4%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #187default of 2064.9%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #179default of 22638.8%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #58high of 6316.9%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #183default of 38717.4%
  2. #222none of 38710.6%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #175default of 23821.0%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #186default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #105high of 1050.0%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #346default of 61011.3
  2. #401none of 6109.0

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #9default of 177$0.02

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #14default of 177$42.50

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #209default of 2100.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #232default of 288362

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #182default of 39948.2%
  2. #321none of 39932.8%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #272default of 52621.7%
  2. #365none of 52616.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #193default of 52633.5%
  2. #263none of 52622.0%

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

knowledge

GPQA Diamond

539 results
  1. #223default of 53976.9%
  2. #381none of 53957.1%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #210default of 26556.8%
  2. #235none of 26546.5%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #309default of 52349.7%
  2. #380none of 52328.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #289default of 5290.3%
  2. #298none of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #73high of 1711.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #39high of 18199.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #35default of 3510.8s
  2. #47none of 3510.9s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #89default of 351155.5
  2. #94none of 351151.0

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #10high of 1770.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #21high of 176107.1

Leader: Muse Spark 1.1 · 204.3