priorsBuilder

Google · released 2026-06-10

DiffusionGemma 26B A4B

Measured on 12 benchmarks.

General frontier

12.7

#127 of 136 models

includes estimates: 24% of the mix is measured for this model

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #299default of 58710.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #436default of 526-59.2

Leader: Opus 5.5 · 46.4

All 12 benchmarks

show 10 more

coding

Terminal-Bench v2.1-AA

238 results
  1. #191default of 23812.4%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #384default of 6109.5

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #236default of 288321

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #127default of 39959.5%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #364default of 52616.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #416default of 5269.1%

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

knowledge

GPQA Diamond

539 results
  1. #316default of 53966.9%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #166default of 26566.5%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #418default of 52319.7%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #296default of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%