priorsBuilder

Google · released 2025-09-25

Gemini 2.5 Flash-Lite

Measured on 43 benchmarks.

General frontier

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

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #364default of 5877.0%
  2. #433none of 5875.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #326none of 526-42.6
  2. #342default of 526-45.6

Leader: Opus 5.5 · 46.4

All 43 benchmarks

show 41 more

agentic

τ²-Bench Telecom

393 results
  1. #254default of 39330.7%
  2. #257none of 39330.4%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #70default of 28268.8%
  2. #89none of 28264.1%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #84none of 12771.4%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #206default of 38712.9%
  2. #237none of 3877.6%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #105none of 12735.2%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #367default of 61010.4
  2. #388none of 6109.3

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #137none of 2201379

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #138none of 2201373

Leader: Gemini 4 · 1553

economics

CorpFin (Vals)

117 results
  1. #83none of 11757.6%

Leader: Opus 5 · 73.2%

economics

MortgageTax (Vals)

84 results
  1. #68none of 8457.6%

Leader: Opus 5 · 72.1%

economics

TaxEval (Vals)

125 results
  1. #103none of 12566.2%

Leader: Muse Spark 1.2 · 80.4%

instruction

IFBench

399 results
  1. #158default of 39952.6%
  2. #239none of 39941.8%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #334default of 52618.0%
  2. #391none of 52615.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #190none of 52633.9%
  2. #258default of 52622.6%

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

knowledge

Global-MMLU-Lite

118 results
  1. #47default of 11883.8%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #284default of 53970.9%
  2. #334none of 53965.1%

Leader: GPT-6 Astra · 96.3%

knowledge

GPQA Diamond (Vals)

122 results
  1. #89none of 12270.2%

Leader: Gemini 3.1 Pro · 95.5%

knowledge

MedCode

94 results
  1. #73none of 9434.2%

Leader: Opus 5 · 63.6%

knowledge

MedQA (Vals)

80 results
  1. #47none of 8088.9%

Leader: o1 · 96.5%

knowledge

MedScribe

96 results
  1. #70none of 9675.8%

Leader: Opus 5.5 · 91.4%

knowledge

MMLU Pro (Vals)

122 results
  1. #92none of 12279.1%

Leader: Fable 5.1 · 92.4%

knowledge

MMLU-Pro

285 results
  1. #83default of 28580.8%
  2. #103none of 28579.6%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU Pro (Vals)

81 results
  1. #53none of 8175.4%

Leader: Fable 5.1 · 90.6%

knowledge

MMMU-Pro

265 results
  1. #172default of 26565.0%
  2. #181none of 26563.4%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #247default of 52364.7%
  2. #310none of 52349.7%

Leader: Kimi K3 · 88.7%

long-context

MLCR-AA

94 results
  1. #85default of 942.2%

Leader: Sonnet 5.5 · 75.0%

math

AIME (Vals)

82 results
  1. #63none of 8242.1%

Leader: Gemini 3.1 Pro · 98.1%

math

AIME 2025

228 results
  1. #88default of 22868.7%
  2. #123none of 22846.7%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #25default of 16296.9%
  2. #49none of 16292.6%

Leader: GPT-5 · 99.4%

math

MGSM (Vals)

62 results
  1. #37none of 6289.5%

Leader: Opus 4.5 · 95.2%

other

Arena Vision

116 results
  1. #86none of 1161188

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #66none of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

CritPt

529 results
  1. #378default of 5290.0%
  2. #392none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #73none of 13582.0%

Leader: Fable 5 · 88.6%

reasoning

SAGE

80 results
  1. #73none of 8030.8%

Leader: Opus 4.7 · 56.1%

reliability

Tool-call error rate

171 results
  1. #134none of 1714.0%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #87none of 18199.6%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #1none of 3510.3s
  2. #270default of 35117s

Leader: this model · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #10default of 351328.5
  2. #17none of 351289.8

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #19none of 1770.5s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #3none of 176152.8

Leader: Muse Spark 1.1 · 204.3