priorsBuilder

Google · released 2026-07-21

Gemini 3.5 Flash-Lite

Measured on 70 benchmarks across 3 reasoning efforts.

General frontier

58.4

#19 of 136 models · best at xhigh

includes estimates: 5% of the mix is measured for this model

Reasoning efforts in your mix

xhigh58.4#47 of 313
minimal39.7#147 of 313
high24.3#256 of 313

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #218high of 58718.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #104high of 5265.2

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #34minimal of 19666.0%
  2. #48xhigh of 19660.0%

Leader: Opus 4.8 · 95.0%

math

FrontierMath Tier 4 (v2)

70 results
  1. #68high of 700.0%

Leader: GPT-6.1 Sol · 100.0%

All 70 benchmarks

show 66 more

agentic

AA-Briefcase v1.1

224 results
  1. #166high of 224650

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench (Zapier)

115 results
  1. #97medium of 1154.0%
  2. #101high of 1153.4%
  3. #115low of 1150.0%

Leader: Gemini 4 · 51.3%

agentic

AutomationBench-AA

219 results
  1. #121high of 21925.0%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #23high of 5042.3%

Leader: Fable 5 · 51.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #66high of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #65high of 7813.9%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #60high of 697.3%

Leader: Fable 5.1 · 49.2%

agentic

τ³-Banking

206 results
  1. #109high of 20617.5%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena Image-to-WebDev

58 results
  1. #46xhigh of 581447

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #67xhigh of 1221440

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #69high of 776.1%

Leader: Sonnet 5.5 · 69.8%

coding

LiveCodeBench (Vals)

127 results
  1. #75high of 12779.0%

Leader: Fable 5.1 · 90.5%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #57high of 620.0%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #44high of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #49high of 6233.9%

Leader: Opus 5.5 · 87.0%

coding

SciCode

226 results
  1. #162high of 22641.3%

Leader: Opus 5.5 · 66.9%

coding

SWE-bench Verified (Vals)

85 results
  1. #42high of 8575.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #57high of 7450.2%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench Science-AA

46 results
  1. #44high of 460.0%

Leader: GPT-6 Astra · 63.3%

coding

Terminal-Bench v2.1-AA

238 results
  1. #112high of 23853.6%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #132high of 2161.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #61high of 10537.2%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #93xhigh of 12739.0%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #200high of 61022.2

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #61xhigh of 2201455

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #57xhigh of 2201467

Leader: Gemini 4 · 1553

cost

AA Intelligence Index Cost per Task

177 results
  1. #56high of 177$0.19

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #60high of 177$366

Leader: GPT-6 Luna · $10.63

creative

MineBench

72 results
  1. #44xhigh of 721387

Leader: GPT-6 Astra Pro · 2281

economics

CorpFin (Vals)

117 results
  1. #65high of 11760.7%

Leader: Opus 5 · 73.2%

economics

Excel Modeling Benchmark

74 results
  1. #58high of 7443.2%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #51high of 7847.4%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #100high of 21013.6%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #165high of 288983

Leader: Opus 5.5 · 1866

economics

MortgageTax (Vals)

84 results
  1. #12high of 8468.7%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #59high of 12572.6%

Leader: Muse Spark 1.2 · 80.4%

knowledge

AA-Omniscience Accuracy

526 results
  1. #182high of 52629.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #60high of 52665.6%

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

knowledge

GPQA Diamond

539 results
  1. #153high of 53983.8%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #56high of 12283.8%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

Harvey LAB-AA v1.1

27 results
  1. #27high of 270.0%

Leader: Muse Wonder Full (Max) · 13.1%

knowledge

MedCode

94 results
  1. #41high of 9443.5%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #82high of 9670.9%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #53high of 12285.8%

Leader: Fable 5.1 · 92.4%

knowledge

MMMU Pro (Vals)

81 results
  1. #30high of 8183.6%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #62high of 26579.0%

Leader: Opus 5.5 · 87.7%

knowledge

Public Benefits Bench v1.1

50 results
  1. #44high of 5051.8%

Leader: Opus 5 · 76.9%

long-context

AA-LCR v1.1

523 results
  1. #149high of 52376.0%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #73high of 947.2%

Leader: Sonnet 5.5 · 75.0%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #76high of 11526.0%

Leader: GPT-6.1 Sol · 93.7%

other

Arena Vision

116 results
  1. #39xhigh of 1161266

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #36xhigh of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #150high of 21553.5%
  2. #177medium of 21532.3%
  3. #187low of 21517.0%
  4. #199minimal of 2157.5%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #138high of 21610.3%
  2. #152medium of 2165.3%
  3. #183low of 2161.5%
  4. #193minimal of 2160.8%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #314high of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #39high of 13584.1%

Leader: Fable 5 · 88.6%

reasoning

Roboflow Visual Reasoning

102 results
  1. #41high of 10268.9%
  2. #82low of 10248.3%

Leader: GPT-6 Astra · 91.2%

reasoning

SAGE

80 results
  1. #32high of 8047.3%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #25xhigh of 4733.1%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #99xhigh of 1711.8%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #61xhigh of 18199.9%

Leader: GPT-5 Pro · 100.0%

safety

CyberBench v1.1

45 results
  1. #36high of 4559.1%

Leader: Wonder · 80.4%

speed

Latency (Time to First Token)

351 results
  1. #244high of 3518.1s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #4high of 351415.6

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #56xhigh of 1770.9s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #6xhigh of 176136.0

Leader: Muse Spark 1.1 · 204.3