priorsBuilder

OpenAI · released 2025-04-16

o3

Measured on 50 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. #207default of 58720.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #217default of 526-15.6

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #133medium of 19626.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #50high of 9753.1%

Leader: Opus 5.5 · 88.4%

All 50 benchmarks

show 46 more

agentic

OSWorld-Verified

13 results
  1. #12high of 1323.0%

Leader: Fable 5 · 86.0%

agentic

τ²-Bench Telecom

393 results
  1. #122default of 39380.7%

Leader: GLM 5.2 · 99.1%

coding

Drone-Bench

11 results
  1. #9high of 1155.0%

Leader: Opus 5.5 · 97.3%

coding

LiveCodeBench

282 results
  1. #25default of 28280.8%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #45high of 12783.9%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #70default of 38737.1%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #58high of 12752.4%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #226default of 61020.2

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #91high of 2201432

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #105high of 2201420

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #72high of 11759.7%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #37high of 8465.7%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #34high of 12574.6%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #55default of 39971.4%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #131default of 52638.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #371default of 52611.9%

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

knowledge

Arena Search

28 results
  1. #23high of 281144

Leader: GPT-5.6 Sol · 1257

knowledge

GPQA Diamond

539 results
  1. #167default of 53982.7%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #54high of 12284.1%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #32high of 9447.3%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #6high of 8096.1%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #65high of 9676.7%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #55high of 12285.6%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #27default of 28585.3%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #43high of 8180.4%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #144default of 26570.1%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #159default of 52374.7%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #37high of 8285.3%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #33default of 22888.3%

Leader: GPT-5.2 · 99.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #67high of 11533.3%
  2. #71medium of 11529.8%
  3. #89low of 11519.3%

Leader: GPT-6.1 Sol · 93.7%

math

MATH 500 (Vals)

48 results
  1. #8high of 4894.6%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #2default of 16299.2%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #22high of 6291.7%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #72high of 1161216

Leader: Fable 5 · 1308

reasoning

ARC-AGI-1

215 results
  1. #138high of 21560.8%
  2. #149medium of 21553.8%
  3. #161low of 21541.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #146high of 2166.5%
  2. #168medium of 2163.0%
  3. #175low of 2162.0%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #221default of 5291.1%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #48high of 13583.8%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #55high of 8041.8%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #15high of 4752.3%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #5high of 1710.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #8high of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #237default of 3516.7s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #108default of 351128.9

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #136high of 1772.5s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #93high of 17660.0

Leader: Muse Spark 1.1 · 204.3