priorsBuilder

Google · released 2025-06-17

Gemini 2.5 Pro

Measured on 74 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. #193default of 58722.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #219default of 526-16.4

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #144medium of 19620.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #69high of 700.0%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #29high of 9762.4%

Leader: Opus 5.5 · 88.4%

All 74 benchmarks

show 69 more

agentic

AA-Briefcase v1.1

224 results
  1. #192default of 224302

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #175default of 2192.2%

Leader: Gemini 4 · 77.5%

agentic

Butter-Bench

5 results
  1. #1high of 540.0%

Leader: this model · 40.0%

agentic

Terminal-Bench 2.0

40 results
  1. #30high of 4032.6%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #55high of 67$574

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #191default of 39354.1%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #147default of 2069.7%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #58high of 581285

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #117high of 1221227

Leader: Opus 5.5 · 1813

coding

LiveCodeBench

282 results
  1. #27default of 28280.1%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #74high of 12779.2%

Leader: Fable 5.1 · 90.5%

coding

SciCode

226 results
  1. #133default of 22646.3%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #79high of 8554.4%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #43high of 6330.3%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #134default of 38726.5%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #160default of 23828.5%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #170default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #101high of 1050.4%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #55high of 12754.0%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #270default of 61016.1

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #72high of 2201445

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #80high of 2201448

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #73default of 177$0.33

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #87default of 177$823

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #57high of 721174

Leader: GPT-6 Astra Pro · 2281

creative

VoxelBench (image)

16 results
  1. #11high of 161219

Leader: GPT-6.1 Sol · 2214

creative

VoxelBench (text)

55 results
  1. #45high of 551299

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #64high of 11760.8%

Leader: Opus 5 · 73.2%

economics

GDP.pdf

210 results
  1. #128default of 21010.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #221default of 288455

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #9high of 8468.9%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #55high of 12572.9%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #179default of 39948.7%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #127default of 52639.1%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #417default of 5269.1%

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

knowledge

Arena Search

28 results
  1. #24high of 281142

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #15high of 5363.9%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #13default of 11890.3%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #143default of 53984.4%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #67high of 12280.8%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #17high of 9450.6%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #24high of 8093.1%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #75high of 9673.6%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #66high of 12284.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #18default of 28586.2%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #40high of 8181.3%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #102default of 26574.9%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #226default of 52369.0%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #35high of 431421

Leader: Opus 5 · 1516

math

AIME (Vals)

82 results
  1. #35high of 8285.8%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #38default of 22887.7%

Leader: GPT-5.2 · 99.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #79high of 11524.6%

Leader: GPT-6.1 Sol · 93.7%

math

MATH 500 (Vals)

48 results
  1. #5high of 4895.2%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #9default of 16298.6%

Leader: GPT-5 · 99.4%

other

Arena Vision

116 results
  1. #53high of 1161248

Leader: Fable 5 · 1308

other

Poker Agent

17 results
  1. #12high of 171033

Leader: GPT-5.2 · 1132

other

T3 Code usage share

85 results
  1. #42high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #162high of 21541.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #155high of 2164.9%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #189default of 5292.6%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #34high of 13584.3%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #56high of 10262.3%
  2. #87low of 10242.4%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #54high of 8041.9%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #152high of 1716.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #172high of 18195.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #288default of 35124s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #127default of 351117.9

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #165high of 1774.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #75high of 17672.8

Leader: Muse Spark 1.1 · 204.3