priorsBuilder

OpenAI · released 2025-01-31

o3 mini

Measured on 46 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #274high of 58712.0%
  2. #344default of 5877.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #325high of 526-42.6

Leader: Opus 5.5 · 46.4

math

FrontierMath Tier 4 (v2)

70 results
  1. #70high of 700.0%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #87high of 9722.8%

Leader: Opus 5.5 · 88.4%

All 46 benchmarks

show 42 more

agentic

AA-Briefcase v1.1

224 results
  1. #202high of 224142

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #200high of 2190.5%

Leader: Gemini 4 · 77.5%

agentic

τ²-Bench Telecom

393 results
  1. #253high of 39331.3%
  2. #262default of 39328.7%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #185high of 2065.2%

Leader: Qwen 3.8 Max · 51.3%

coding

LiveCodeBench

282 results
  1. #49high of 28273.4%
  2. #55default of 28271.7%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #83high of 12771.5%

Leader: Fable 5.1 · 90.5%

coding

SciCode

226 results
  1. #154high of 22642.8%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #242default of 3876.8%
  2. #256high of 3876.1%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #210high of 2384.5%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #189high of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

WeirdML v2

127 results
  1. #76high of 12743.7%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #323default of 61012.5
  2. #357high of 61011.0

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #146high of 2201364

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #152high of 2201345

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #105high of 11745.3%

Leader: Opus 5 · 73.2%

economics

GDP.pdf

210 results
  1. #183high of 2102.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #247high of 288230

Leader: Opus 5.5 · 1866

economics

TaxEval (Vals)

125 results
  1. #89high of 12569.4%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #89high of 39967.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #275high of 52621.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #284high of 52618.9%

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

knowledge

GPQA Diamond

539 results
  1. #218high of 53977.3%
  2. #253default of 53974.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #78high of 12275.5%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedQA (Vals)

80 results
  1. #14high of 8094.8%

Leader: o1 · 96.5%

knowledge

MMLU Pro (Vals)

122 results
  1. #94high of 12278.7%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #94high of 28580.2%
  2. #108default of 28579.1%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #329high of 52343.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #32high of 8286.5%

Leader: Gemini 3.1 Pro · 98.1%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #91high of 11518.6%
  2. #101medium of 11510.5%
  3. #110low of 1153.9%

Leader: GPT-6.1 Sol · 93.7%

math

MATH 500 (Vals)

48 results
  1. #18high of 4891.8%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #10high of 16298.5%
  2. #22default of 16297.3%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #24high of 6291.3%

Leader: Opus 4.5 · 95.2%

reasoning

ARC-AGI-1

215 results
  1. #171high of 21534.5%
  2. #181medium of 21522.3%
  3. #190low of 21514.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #167high of 2163.0%
  2. #174medium of 2162.1%
  3. #208low of 2160.0%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #292high of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #109high of 13571.5%

Leader: Fable 5 · 88.6%

reliability

Tool-call error rate

171 results
  1. #81high of 1711.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #10high of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #239default of 3516.7s
  2. #280high of 35120s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #44default of 351197.7
  2. #47high of 351196.9

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #147high of 1773.0s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #7high of 176135.0

Leader: Muse Spark 1.1 · 204.3