priorsBuilder

Google · released 2025-12-17

Gemini 3 Flash

Measured on 77 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. #108default of 58736.6%
  2. #245none of 58715.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #93default of 52610.1
  2. #153none of 526-4.3

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #172high of 19610.0%
  2. #175none of 19610.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #54high of 7017.1%

Leader: GPT-6.1 Sol · 100.0%

reasoning

SimpleBench

97 results
  1. #33high of 9761.1%

Leader: Opus 5.5 · 88.4%

All 77 benchmarks

show 72 more

agentic

APEX-Agents-AA

33 results
  1. #16default of 3327.7%

Leader: Gemini 3.5 Flash · 47.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #65high of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #56high of 7818.3%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #53high of 6911.8%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 2.0

40 results
  1. #9high of 4064.3%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #44high of 67$3,635

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #125default of 39380.4%
  2. #219none of 39343.3%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #96default of 20620.8%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #45high of 581451
  2. #51minimal of 581431

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #69high of 1221439
  2. #90minimal of 1221385

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #68high of 776.4%

Leader: Sonnet 5.5 · 69.8%

coding

DeepSWE v1

29 results
  1. #26high of 295.1%

Leader: GPT-5.5 · 70.0%

coding

LiveCodeBench

282 results
  1. #2default of 28290.8%
  2. #29none of 28279.7%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #30high of 12785.6%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #55high of 620.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #40high of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #50high of 6233.8%

Leader: Opus 5.5 · 87.0%

coding

SWE Atlas-QnA

22 results
  1. #22high of 228.2%

Leader: Opus 5 · 63.2%

coding

SWE-bench Verified (Vals)

85 results
  1. #41high of 8575.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #17high of 6351.7%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #51high of 7453.9%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #61default of 38738.6%
  2. #103none of 38731.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #73high of 10520.2%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #41high of 12761.6%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #148default of 61026.3
  2. #252none of 61017.9

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #42high of 2201473
  2. #55minimal of 2201458

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #35high of 2201482
  2. #47minimal of 2201474

Leader: Gemini 4 · 1553

composite

Vals Multimodal Index v1.2

33 results
  1. #24high of 3352.2%

Leader: Fable 5 · 74.2%

creative

MineBench

72 results
  1. #49high of 721291

Leader: GPT-6 Astra Pro · 2281

creative

VoxelBench (text)

55 results
  1. #47high of 551284

Leader: GPT-6 Astra · 2732

economics

CorpFin (Vals)

117 results
  1. #20high of 11766.4%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #66high of 7426.0%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #58high of 7842.6%

Leader: Gemini 4 · 65.4%

economics

MortgageTax (Vals)

84 results
  1. #11high of 8468.7%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #44high of 12573.9%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #14default of 39978.0%
  2. #146none of 39955.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #47default of 52653.4%
  2. #83none of 52645.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #457none of 5267.6%
  2. #469default of 5267.0%

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

knowledge

Arena Search

28 results
  1. #14high of 281198

Leader: GPT-5.6 Sol · 1257

knowledge

CaseLaw (Vals)

53 results
  1. #33high of 5355.8%

Leader: Grok 4.3 · 79.3%

knowledge

Global-MMLU-Lite

118 results
  1. #2none of 11892.7%
  2. #5default of 11891.4%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #69default of 53989.8%
  2. #180none of 53981.2%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #37high of 12287.9%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #5high of 9455.9%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #11high of 8095.8%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #84high of 9669.9%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #19high of 12288.6%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #4default of 28589.0%
  2. #6none of 28588.2%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #13high of 8187.6%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #51default of 26579.9%
  2. #68none of 26578.6%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #121default of 52378.0%
  2. #286none of 52355.3%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #39high of 431413

Leader: Opus 5 · 1516

long-context

MLCR-AA

94 results
  1. #61none of 9411.7%
  2. #63default of 9411.1%

Leader: Sonnet 5.5 · 75.0%

math

AIME (Vals)

82 results
  1. #8high of 8295.6%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #3default of 22897.0%
  2. #110none of 22855.7%

Leader: GPT-5.2 · 99.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #49high of 11551.2%

Leader: GPT-6.1 Sol · 93.7%

math

MGSM (Vals)

62 results
  1. #8high of 6293.3%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #35high of 1161273
  2. #46minimal of 1161260

Leader: Fable 5 · 1308

other

Poker Agent

17 results
  1. #3high of 171100

Leader: GPT-5.2 · 1132

other

T3 Code usage share

85 results
  1. #33high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #99high of 21584.7%
  2. #143medium of 21557.7%
  3. #179low of 21529.0%
  4. #182minimal of 21521.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #109high of 21633.6%
  2. #135medium of 21612.8%
  3. #166minimal of 2163.3%
  4. #188low of 2161.3%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #129default of 5298.6%
  2. #208none of 5291.4%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #10high of 13586.9%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #25high of 10274.2%
  2. #51low of 10264.9%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #10high of 8051.8%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #129high of 1713.7%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #175high of 18194.8%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #42none of 3510.9s
  2. #235default of 3516.3s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #36none of 351206.3
  2. #38default of 351204.8

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #91high of 1771.3s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #37high of 17696.0

Leader: Muse Spark 1.1 · 204.3