priorsBuilder

Google · released 2026-04-02

Gemma 4 31B

Measured on 37 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. #186default of 58723.6%
  2. #279none of 58711.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #356default of 526-47.9
  2. #387none of 526-51.7

Leader: Opus 5.5 · 46.4

All 37 benchmarks

show 35 more

agentic

AA-Briefcase v1.1

224 results
  1. #186default of 224368

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench (Zapier)

115 results
  1. #107max of 1151.7%

Leader: Gemini 4 · 51.3%

agentic

AutomationBench-AA

219 results
  1. #161default of 2194.9%

Leader: Gemini 4 · 77.5%

agentic

EnterpriseOps-Gym-AA

50 results
  1. #45default of 5028.3%

Leader: Fable 5 · 51.1%

agentic

ITBench-AA

45 results
  1. #25default of 4537.3%

Leader: GPT-5.6 Sol · 56.2%

agentic

τ²-Bench Telecom

393 results
  1. #173none of 39365.5%
  2. #184default of 39359.9%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #122default of 20614.8%
  2. #154none of 2068.9%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena WebDev

122 results
  1. #93max of 1221366

Leader: Opus 5.5 · 1813

coding

SciCode

226 results
  1. #138default of 22645.5%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #73default of 38736.4%
  2. #117none of 38730.3%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #135default of 23843.4%
  2. #158none of 23829.2%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #174default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #288default of 61014.7
  2. #299none of 61013.9

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #65max of 2201452

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #61max of 2201466

Leader: Gemini 4 · 1553

creative

MineBench

72 results
  1. #52max of 721260

Leader: GPT-6 Astra Pro · 2281

economics

GDP.pdf

210 results
  1. #151default of 2106.0%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #202default of 288619
  2. #209none of 288547

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #30default of 39975.6%
  2. #155none of 39953.5%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #296default of 52620.0%
  2. #363none of 52616.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #299none of 52618.1%
  2. #331default of 52615.0%

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

knowledge

GPQA Diamond

539 results
  1. #125default of 53985.7%
  2. #233none of 53976.3%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #119default of 26573.4%
  2. #141none of 26570.3%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #218default of 52369.7%
  2. #315none of 52346.7%

Leader: Kimi K3 · 88.7%

long-context

Arena Document

43 results
  1. #34max of 431425

Leader: Opus 5 · 1516

other

Arena Vision

116 results
  1. #43max of 1161262

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #210default of 5291.4%
  2. #339none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Roboflow Visual Reasoning

102 results
  1. #77low of 10252.8%

Leader: GPT-6 Astra · 91.2%

reasoning

SimpleQA Verified

47 results
  1. #42max of 4710.7%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

171 results
  1. #114max of 1712.5%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #171max of 18196.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #76default of 3511.0s
  2. #155none of 3512.0s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #308none of 35144.6
  2. #335default of 35135.1

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #41max of 1770.8s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #155max of 17632.0

Leader: Muse Spark 1.1 · 204.3