priorsBuilder

Google · released 2025-05-20

Gemini 2.5 Flash

Measured on 52 benchmarks.

General frontier

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

Your mix’s benchmarks

4 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #257default of 58713.8%
  2. #335none of 5878.7%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #270default of 526-29.8
  2. #311none of 526-39.9

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #150medium of 19619.0%

Leader: Opus 4.8 · 95.0%

reasoning

SimpleBench

97 results
  1. #65medium of 9741.2%

Leader: Opus 5.5 · 88.4%

All 52 benchmarks

show 48 more

agentic

Terminal-Bench 2.0

40 results
  1. #38medium of 4017.1%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #56medium of 67$549

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #214default of 39345.6%
  2. #263none of 39328.4%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #57default of 28271.3%
  2. #97none of 28262.5%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #79medium of 12776.2%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #55medium of 6321.3%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #184default of 38716.7%
  2. #195none of 38714.4%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #82medium of 12741.9%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #278default of 61015.5
  2. #326none of 61012.4

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #116medium of 2201409

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #122medium of 2201403

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #71medium of 11759.8%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #50medium of 8462.6%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #57medium of 12572.7%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #160default of 39952.3%
  2. #221none of 39943.5%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #195default of 52628.3%
  2. #205none of 52626.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #240default of 52624.7%
  2. #427none of 5268.8%

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

knowledge

Global-MMLU-Lite

118 results
  1. #23default of 11888.8%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #197default of 53979.3%
  2. #228none of 53976.6%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #64medium of 12281.6%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #59medium of 9440.5%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #35medium of 8091.4%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #44medium of 9683.0%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #68medium of 12283.7%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #36default of 28584.2%
  2. #44none of 28583.6%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #42medium of 8180.8%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #122default of 26573.1%
  2. #143none of 26570.2%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #204default of 52371.0%
  2. #274none of 52360.0%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #69default of 948.9%
  2. #71none of 948.3%

Leader: Sonnet 5.5 · 75.0%

math

AIME (Vals)

82 results
  1. #58medium of 8251.5%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #66default of 22878.3%
  2. #102none of 22860.3%

Leader: GPT-5.2 · 99.0%

math

MATH 500 (Vals)

48 results
  1. #19medium of 4891.8%

Leader: Gemini 3 Pro · 96.4%

math

MATH-500

162 results
  1. #15default of 16298.1%
  2. #46none of 16293.2%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #35medium of 6289.9%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #66medium of 1161229

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #41medium of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

ARC-AGI-1

215 results
  1. #174medium of 21533.3%

Leader: Fable 5 · 98.5%

reasoning

ARC-AGI-2

216 results
  1. #171medium of 2162.5%

Leader: GPT-6 Astra · 95.0%

reasoning

CritPt

529 results
  1. #213none of 5291.4%
  2. #227default of 5291.1%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #46medium of 13583.8%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #44medium of 8044.8%

Leader: Opus 4.7 · 56.1%

reasoning

SimpleQA Verified

47 results
  1. #32medium of 4728.1%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #148medium of 1715.4%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #158medium of 18197.4%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #6none of 3510.5s
  2. #275default of 35119s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #30default of 351211.6
  2. #41none of 351200.6

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #40medium of 1770.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #32medium of 17699.8

Leader: Muse Spark 1.1 · 204.3