priorsBuilder

Other · released 2026-07-23

G9v3-3B

Measured on 9 benchmarks.

General frontier

19.2

#112 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. #483default of 5874.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #155default of 526-4.4

Leader: Opus 5.5 · 46.4

All 9 benchmarks

show 7 more

coding

Terminal-Bench v2.1-AA

238 results
  1. #204default of 2386.0%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #359default of 61010.8

Leader: Opus 5.5 · 57.6

knowledge

AA-Omniscience Accuracy

526 results
  1. #507default of 5266.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #2default of 52688.3%

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

knowledge

GPQA Diamond

539 results
  1. #438default of 53943.8%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #339default of 52341.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #374default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%