priorsBuilder

Other · released 2026-08-20

G9v3-39A5B

Measured on 12 benchmarks.

General frontier

24.8

#93 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. #228default of 58717.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #111default of 5263.8

Leader: Opus 5.5 · 46.4

All 12 benchmarks

show 10 more

agentic

τ³-Banking

206 results
  1. #91default of 20622.1%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #187default of 22636.8%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #152default of 23832.6%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #203default of 61021.8

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #136default of 2881105

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #406default of 52614.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #3default of 52687.0%

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

knowledge

GPQA Diamond

539 results
  1. #189default of 53980.5%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #242default of 52365.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #266default of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%