priorsBuilder

Google · released 2026-03-03

Gemini 3.1 Flash-Lite

Measured on 69 benchmarks.

General frontier

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

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #229high of 58717.2%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #221high of 526-16.4

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #170medium of 19611.0%

Leader: Opus 4.8 · 95.0%

All 69 benchmarks

show 66 more

agentic

AA-AnalystAgent

44 results
  1. #41high of 448.8%

Leader: Gemini 3.7 Flash · 60.0%

agentic

AA-Briefcase v1.1

224 results
  1. #199high of 224207

Leader: Sonnet 5.5 · 1823

agentic

APEX-Agents-AA

33 results
  1. #27high of 3312.2%

Leader: Gemini 3.5 Flash · 47.1%

agentic

AutomationBench-AA

219 results
  1. #153high of 2196.8%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #46high of 5028.0%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #63high of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #74high of 783.4%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #67high of 693.1%

Leader: Fable 5.1 · 49.2%

agentic

τ²-Bench Telecom

393 results
  1. #252high of 39331.3%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #148high of 2069.7%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #57high of 581337

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #111high of 1221256

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #72high of 774.6%

Leader: Sonnet 5.5 · 69.8%

coding

LiveCodeBench (Vals)

127 results
  1. #71high of 12780.1%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #56high of 620.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #41high of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #59high of 6214.3%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #149high of 22643.4%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #72high of 8562.8%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #51high of 6324.7%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #70high of 7434.1%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Hard-AA

387 results
  1. #145high of 38724.2%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #153high of 23831.1%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #144high of 2160.5%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #102high of 1050.0%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #61high of 12752.2%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #276high of 61015.6

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #90high of 2201433

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #91high of 2201436

Leader: Gemini 4 · 1553

composite

Vals Multimodal Index v1.2

33 results
  1. #31high of 3341.4%

Leader: Fable 5 · 74.2%

cost

AA Intelligence Index Cost per Task

177 results
  1. #27high of 177$0.06

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #37high of 177$156

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #67high of 72991

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #76high of 11759.4%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #74high of 748.6%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #71high of 7830.0%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #143high of 2107.8%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #224high of 288430

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #20high of 8468.0%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #70high of 12571.8%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #17high of 39977.2%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #148high of 52636.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #310high of 52617.3%

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

knowledge

CaseLaw (Vals)

53 results
  1. #35high of 5355.0%

Leader: Grok 4.3 · 79.3%

knowledge

GPQA Diamond

539 results
  1. #173high of 53982.2%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #66high of 12281.1%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #30high of 9447.6%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #89high of 9663.9%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #44high of 12286.2%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #37high of 8182.5%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #93high of 26575.5%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #165high of 52374.3%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #77high of 946.1%

Leader: Sonnet 5.5 · 75.0%

math

AIME (Vals)

82 results
  1. #43high of 8283.3%

Leader: Gemini 3.1 Pro · 98.1%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #74high of 11527.7%
  2. #81low of 11522.5%
  3. #83minimal of 11521.4%

Leader: GPT-6.1 Sol · 93.7%

other

Arena Vision

116 results
  1. #63high of 1161235

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #35high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

CritPt

529 results
  1. #226high of 5291.1%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #47high of 13583.8%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #20high of 8049.5%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #137high of 1714.7%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #161high of 18197.1%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #228high of 3514.9s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #5high of 351365.0

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #42high of 1770.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #11high of 176123.8

Leader: Muse Spark 1.1 · 204.3