priorsBuilder

Google · released 2026-04-02

Gemma 4 26B

Measured on 33 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. #214default of 58719.3%
  2. #282none of 58711.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #379default of 526-50.8
  2. #455none of 526-62.3

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #140xhigh of 19621.0%
  2. #169none of 19611.0%

Leader: Opus 4.8 · 95.0%

All 33 benchmarks

show 30 more

agentic

AA-Briefcase v1.1

224 results
  1. #189default of 224315

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #178default of 2191.9%

Leader: Gemini 4 · 77.5%

agentic

ITBench-AA

45 results
  1. #38default of 4523.6%

Leader: GPT-5.6 Sol · 56.2%

agentic

τ²-Bench Telecom

393 results
  1. #218default of 39343.6%
  2. #225none of 39340.4%

Leader: GLM 5.2 · 99.1%

agentic

τ³-Banking

206 results
  1. #136default of 20612.0%

Leader: Qwen 3.8 Max · 51.3%

coding

Arena WebDev

122 results
  1. #96xhigh of 1221359

Leader: Opus 5.5 · 1813

coding

SciCode

226 results
  1. #171default of 22640.0%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench Hard-AA

387 results
  1. #142none of 38725.0%
  2. #199default of 38713.6%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #143default of 23839.0%

Leader: Fable 5.1 · 91.4%

coding

WeirdML v2

127 results
  1. #106xhigh of 12735.2%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #264default of 61016.7
  2. #310none of 61013.1

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #84xhigh of 2201438

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #79xhigh of 2201448

Leader: Gemini 4 · 1553

economics

GDPval-AA v2.1

288 results
  1. #207default of 288565

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #48default of 39972.4%
  2. #204none of 39945.4%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #306default of 52619.1%
  2. #390none of 52615.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #352default of 52613.6%
  2. #449none of 5267.9%

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

knowledge

GPQA Diamond

539 results
  1. #198default of 53979.2%
  2. #279none of 53971.4%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #149default of 26569.2%
  2. #165none of 26566.7%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #240default of 52365.7%
  2. #333none of 52342.3%

Leader: Kimi K3 · 88.7%

other

Arena Vision

116 results
  1. #60xhigh of 1161242

Leader: Fable 5 · 1308

reasoning

CritPt

529 results
  1. #325default of 5290.0%
  2. #342none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

Roboflow Visual Reasoning

102 results
  1. #83low of 10247.7%

Leader: GPT-6 Astra · 91.2%

reasoning

SimpleQA Verified

47 results
  1. #44xhigh of 479.1%

Leader: Gemini 3.1 Pro · 77.5%

reliability

Tool-call error rate

172 results
  1. #82xhigh of 1721.1%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #111xhigh of 18299.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #62default of 3511.0s
  2. #66none of 3511.0s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #173none of 35196.5
  2. #226default of 35172.3

Leader: Celeris-1 · 1564.1

speed

Provider latency

178 results
  1. #30xhigh of 1780.6s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #117xhigh of 17650.0

Leader: Muse Spark 1.1 · 204.5