priorsBuilder

Google · released 2026-02-19

Gemini 3.1 Pro

Measured on 107 benchmarks.

General frontier

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

Your mix’s benchmarks

7 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #40default of 58747.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #28default of 52631.9

Leader: Opus 5.5 · 46.4

reasoning

ARC-AGI-3

57 results
  1. #39high of 570.4%

Leader: GPT-6 Astra · 99.9%

reasoning

BullshitBench v2

196 results
  1. #105low of 19637.0%
  2. #121high of 19631.0%

Leader: Opus 4.8 · 95.0%

coding

DeepSWE v1.1

70 results
  1. #68high of 7011.7%

Leader: GPT-6 Astra · 74.1%

math

FrontierMath Tier 4 (v2)

70 results
  1. #40high of 7026.8%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #10high of 9779.6%

Leader: Opus 5.5 · 88.4%

All 107 benchmarks

show 100 more

agentic

AA-AnalystAgent

44 results
  1. #19default of 4441.3%

Leader: Gemini 3.7 Flash · 60.0%

agentic

AA-Briefcase v1.1

224 results
  1. #180default of 224456

Leader: Sonnet 5.5 · 1823

agentic

Agent Arena

50 results
  1. #47high of 50-7.8%

Leader: Opus 5.5 · 15.5%

agentic

APEX-Agents-AA

33 results
  1. #11default of 3332.0%

Leader: Gemini 3.5 Flash · 47.1%

agentic

AutomationBench (Zapier)

115 results
  1. #80high of 1158.7%
  2. #85medium of 1157.0%
  3. #94low of 1154.6%

Leader: Gemini 4 · 51.3%

agentic

AutomationBench-AA

219 results
  1. #103default of 21935.4%

Leader: Gemini 4 · 77.5%

agentic

BioMysteryBench

27 results
  1. #26high of 2760.0%

Leader: Sonnet 5.5 · 81.1%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #24default of 5042.2%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #70high of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

ITBench-AA

45 results
  1. #33default of 4530.3%

Leader: GPT-5.6 Sol · 56.2%

agentic

Legal Research Bench

78 results
  1. #55high of 7820.7%

Leader: Muse Spark 1.3 · 55.3%

agentic

PostTrainBench v1.1

12 results
  1. #11high of 1222.0%

Leader: Fable 5 · 41.8%

agentic

Tax Agent Bench

69 results
  1. #56high of 699.3%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 2.0

40 results
  1. #2high of 4080.2%

Leader: GPT-5.5 · 84.7%

agentic

Terminal-Bench 2.1

18 results
  1. #17high of 1865.8%

Leader: GPT-6 Astra · 87.4%

agentic

Terminal-Bench 4.0 (Vals)

47 results
  1. #41high of 472.5%

Leader: Opus 5.5 · 65.2%

agentic

Terminal-Bench Science (Vals)

40 results
  1. #34high of 401.4%

Leader: GPT-6 Astra · 62.9%

agentic

Vending-Bench 2

67 results
  1. #43high of 67$3,774

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #20default of 39395.6%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #93default of 20621.4%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #42high of 581481

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #65high of 1221447

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #53high of 7717.3%

Leader: Sonnet 5.5 · 69.8%

coding

DeepSWE v1

29 results
  1. #24high of 299.7%

Leader: GPT-5.5 · 70.0%

coding

FrontierSWE v1

17 results
  1. #11high of 1734.4%

Leader: Fable 5 · 88.2%

coding

IOI

44 results
  1. #24high of 4451.8%

Leader: Gemini 4 · 100.0%

coding

LiveCodeBench (Vals)

127 results
  1. #6high of 12788.5%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #46high of 621.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #42high of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #48high of 6239.5%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #21default of 22658.7%

Leader: Opus 5.5 · 66.9%

coding

SWE Atlas-QnA

22 results
  1. #19high of 2213.5%

Leader: Opus 5 · 63.2%

coding

SWE-bench Verified (Vals)

85 results
  1. #28high of 8578.8%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #5high of 6367.4%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #27high of 7470.8%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #16default of 38753.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #67default of 23873.8%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #102default of 2164.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench 1-100

22 results
  1. #22high of 226.7%

Leader: Opus 5.5 · 30.4%

coding

Vibe Code Bench v1.1

105 results
  1. #63high of 10532.0%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #28high of 12772.1%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #122default of 61029.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #16high of 2201487

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #11high of 2201497

Leader: Gemini 4 · 1553

composite

Vals Index

47 results
  1. #43high of 4733.4%

Leader: Gemini 4 · 68.9%

composite

Vals Multimodal Index v1.2

33 results
  1. #20high of 3356.1%

Leader: Fable 5 · 74.2%

cost

AA Intelligence Index Cost per Task

177 results
  1. #129default of 177$1.30

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #131default of 177$1,935

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #24high of 721711

Leader: GPT-6 Astra Pro · 2281

creative

VoxelBench (image)

16 results
  1. #2high of 161589

Leader: GPT-6.1 Sol · 2214

creative

VoxelBench (text)

55 results
  1. #25high of 551674

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #37high of 11764.5%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #52high of 7452.6%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #57high of 7843.0%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #76default of 21017.8%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #185default of 288791

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #6high of 8469.4%

Leader: Opus 5 · 72.1%

economics

Public Benefits Bench v1 (Vals)

13 results
  1. #10high of 1350.9%

Leader: Fable 5 · 71.7%

economics

TaxEval (Vals)

125 results
  1. #56high of 12572.9%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #18default of 39977.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #38default of 52654.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #115default of 52649.1%

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

knowledge

Arena Search

28 results
  1. #8high of 281210

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #12high of 5364.8%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #1default of 11893.2%

Leader: this model · 93.2%

knowledge

GPQA Diamond

539 results
  1. #9default of 53994.1%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #1high of 12295.5%

Leader: this model · 95.5%

knowledge

Harvey LAB-AA v1.1

27 results
  1. #23default of 270.0%

Leader: Muse Wonder Full (Max) · 13.1%

knowledge

MedCode

94 results
  1. #2high of 9459.1%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #3high of 8096.4%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #68high of 9676.1%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #4high of 12291.0%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #10high of 8188.2%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #33default of 26582.4%

Leader: Opus 5.5 · 87.7%

knowledge

Public Benefits Bench v1.1

50 results
  1. #43high of 5053.8%

Leader: Opus 5 · 76.9%

long-context

AA-LCR v1.1

523 results
  1. #48default of 52382.0%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #30high of 431444

Leader: Opus 5 · 1516

long-context

MLCR-AA

94 results
  1. #46default of 9415.6%

Leader: Sonnet 5.5 · 75.0%

math

AIME (Vals)

82 results
  1. #1high of 8298.1%

Leader: this model · 98.1%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #36high of 11559.6%

Leader: GPT-6.1 Sol · 93.7%

math

ProofBench v1.1

52 results
  1. #40high of 5226.0%

Leader: Sonnet 5.5 · 100.0%

other

Arena Vision

116 results
  1. #28high of 1161280

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #30high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #9high of 21598.0%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #41high of 21677.1%

Leader: GPT-6 Astra · 95.0%

reasoning

Blueprint-Bench 2

28 results
  1. #22high of 2826.5%

Leader: Gemini 4 · 54.4%

reasoning

CritPt

529 results
  1. #75default of 52917.7%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Furniture Assembly

31 results
  1. #26high of 3126.7%

Leader: Opus 5.5 · 83.3%

reasoning

LegalBench

135 results
  1. #4high of 13587.4%

Leader: Fable 5 · 88.6%

reasoning

MysteryMechanism

27 results
  1. #22high of 2720.7%

Leader: GPT-6 Astra · 53.2%

reasoning

Roboflow Visual Reasoning

102 results
  1. #24high of 10274.8%
  2. #33low of 10272.2%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #26high of 8048.7%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #1high of 4777.5%

Leader: this model · 77.5%

reliability

Tool-call error rate

171 results
  1. #124high of 1713.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #178high of 18193.6%

Leader: GPT-5 Pro · 100.0%

safety

SRE Bench

32 results
  1. #31high of 320.0%

Leader: GPT-6 Astra · 56.9%

speed

Latency (Time to First Token)

351 results
  1. #285default of 35122s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #102default of 351140.2

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #157high of 1773.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #56high of 17680.8

Leader: Muse Spark 1.1 · 204.3