priorsBuilder

Google · released 2025-11-18

Gemini 3 Pro

Measured on 59 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. #85high of 58739.7%
  2. #151low of 58729.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #78high of 52615.3
  2. #119low of 5261.8

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #80low of 19648.0%
  2. #108high of 19636.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #13high of 9776.4%

Leader: Opus 5.5 · 88.4%

All 59 benchmarks

show 55 more

agentic

Terminal-Bench 2.0

40 results
  1. #6high of 4069.4%

Leader: GPT-5.5 · 84.7%

agentic

Terminal-Bench 2.1

18 results
  1. #15high of 1873.9%

Leader: GPT-6 Astra · 87.4%

agentic

Vending-Bench 2

67 results
  1. #25high of 67$5,478

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #81high of 39387.1%
  2. #165low of 39368.1%

Leader: GLM 5.2 · 99.1%

coding

Arena Image-to-WebDev

58 results
  1. #48high of 581441

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #68high of 1221440

Leader: Opus 5.5 · 1813

coding

LiveCodeBench

282 results
  1. #1high of 28291.7%
  2. #12low of 28285.7%

Leader: this model · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #23high of 12786.4%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #37high of 8576.4%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #15high of 6355.1%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #51high of 38741.7%
  2. #89low of 38734.1%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #82high of 10514.3%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #31high of 12769.9%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #135high of 61028.0
  2. #198low of 61022.3

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #18high of 2201485

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #14high of 2201496

Leader: Gemini 4 · 1553

creative

MineBench

72 results
  1. #42high of 721423

Leader: GPT-6 Astra Pro · 2281

creative

VoxelBench (image)

16 results
  1. #6high of 161411

Leader: GPT-6.1 Sol · 2214

creative

VoxelBench (text)

55 results
  1. #44high of 551332

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #44high of 11763.7%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #7high of 8469.1%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #60high of 12572.6%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #66high of 39970.4%
  2. #173low of 39949.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #35high of 52655.8%
  2. #69low of 52648.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #402low of 52610.0%
  2. #435high of 5268.5%

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

knowledge

Arena Search

28 results
  1. #9high of 281207

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #42high of 5353.1%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #3high of 11892.2%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #57high of 53990.8%
  2. #87low of 53988.7%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #19high of 12291.7%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #14high of 9452.2%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #8high of 8096.0%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #81high of 9672.0%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #7high of 12290.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #1high of 28589.8%
  2. #2low of 28589.5%

Leader: this model · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #14high of 8187.5%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #49high of 26580.2%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #146high of 52376.0%
  2. #169low of 52374.0%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #32high of 431434

Leader: Opus 5 · 1516

math

AIME (Vals)

82 results
  1. #4high of 8296.7%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #7high of 22895.7%
  2. #40low of 22886.7%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #1high of 4896.4%

Leader: this model · 96.4%

math

MGSM (Vals)

62 results
  1. #5high of 6293.9%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #12high of 1161289

Leader: Fable 5 · 1308

other

Poker Agent

17 results
  1. #6high of 171079

Leader: GPT-5.2 · 1132

reasoning

ARC-AGI-1

215 results
  1. #115high of 21575.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #116high of 21631.1%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #122high of 5299.1%
  2. #313low of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #6high of 13587.0%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #31high of 8047.6%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #6high of 4772.1%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #156high of 1717.8%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #88high of 18199.6%

Leader: GPT-5 Pro · 100.0%

speed

Provider latency

177 results
  1. #137high of 1772.5s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #42high of 17688.3

Leader: Muse Spark 1.1 · 204.3