priorsBuilder

OpenAI · released 2025-04-16

o4 mini

Measured on 48 benchmarks.

General frontier

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

Your mix’s benchmarks

5 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #234high of 58716.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #293high of 526-35.7

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #184low of 1968.0%
  2. #191high of 1964.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #61high of 704.9%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #69high of 9738.7%

Leader: Opus 5.5 · 88.4%

All 48 benchmarks

show 43 more

agentic

τ²-Bench Telecom

393 results
  1. #188high of 39355.6%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #11high of 28285.9%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #55high of 12782.2%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #191high of 38715.2%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #57high of 12752.6%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #265high of 61016.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #128high of 2201391

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #135high of 2201383

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #77high of 11759.0%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #43high of 8464.8%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #29high of 12574.8%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #78high of 39968.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #228high of 52624.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #278high of 52619.5%

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

knowledge

GPQA Diamond

539 results
  1. #208high of 53978.4%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #81high of 12274.5%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #75high of 9433.8%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #9high of 8096.0%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #85high of 9669.1%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #81high of 12280.6%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #48high of 28583.2%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #45high of 8179.7%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #150high of 26569.2%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #268high of 52361.0%

Leader: Kimi K3 · 88.7%

math

AIME (Vals)

82 results
  1. #41high of 8283.7%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #23high of 22890.7%

Leader: GPT-5.2 · 99.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #62high of 11536.1%
  2. #73medium of 11528.8%
  3. #98low of 11516.1%

Leader: GPT-6.1 Sol · 93.7%

math

MATH 500 (Vals)

48 results
  1. #10high of 4894.2%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #7high of 16298.9%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #7high of 6293.4%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #79high of 1161201

Leader: Fable 5 · 1308

reasoning

ARC-AGI-1

215 results
  1. #140high of 21558.7%
  2. #160medium of 21541.8%
  3. #183low of 21521.3%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #148high of 2166.1%
  2. #172medium of 2162.4%
  3. #179low of 2161.7%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #253high of 5290.6%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #90high of 13579.2%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #56high of 8041.1%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #36high of 4721.2%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #7high of 1710.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #12high of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #282high of 35121s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #86high of 351156.4

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #151high of 1773.3s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #13high of 176122.5

Leader: Muse Spark 1.1 · 204.3