priorsBuilder

Google · released 2026-04-02

Gemma 4 E2B (Reasoning)

Measured on 14 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. #464default of 5874.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #251default of 526-23.6

Leader: Opus 5.5 · 46.4

All 14 benchmarks

show 12 more

agentic

τ²-Bench Telecom

393 results
  1. #319default of 39320.8%

Leader: GLM 5.2 · 99.1%

coding

Terminal-Bench Hard-AA

387 results
  1. #298default of 3873.0%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #230default of 2380.4%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #440default of 6107.8

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #274default of 288-188

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #275default of 39938.0%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #506default of 5266.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #52default of 52667.6%

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

knowledge

GPQA Diamond

539 results
  1. #441default of 53943.3%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #239default of 26544.6%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #428default of 52316.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #426default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%