priorsBuilder

Other · released 2026-08-25

Granite 4.2 3B

Measured on 20 benchmarks.

General frontier

18.2

#117 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. #371default of 5876.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #215default of 526-14.7

Leader: Opus 5.5 · 46.4

All 20 benchmarks

show 18 more

agentic

AA-Briefcase v1.1

224 results
  1. #206default of 22498

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #206default of 2190.4%

Leader: Gemini 4 · 77.5%

agentic

τ³-Banking

206 results
  1. #178default of 2065.6%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #213default of 22625.3%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #188default of 23813.9%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #196default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #395default of 6109.1

Leader: Opus 5.5 · 57.6

cost

AA Intelligence Index Cost per Task

177 results
  1. #2default of 177$0.01

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #3default of 177$14.91

Leader: GPT-6 Luna · $10.63

economics

GDP.pdf

210 results
  1. #207default of 2100.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #251default of 288202

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #478default of 5269.2%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #30default of 52673.7%

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

knowledge

GPQA Diamond

539 results
  1. #387default of 53955.9%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #396default of 52324.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #397default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

speed

Latency (Time to First Token)

351 results
  1. #13default of 3510.6s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #29default of 351214.1

Leader: Celeris-1 · 1522.5