priorsBuilder

Other · released 2026-07-09

JT-4.1 Flash 236B A21B (Non-reasoning)

Measured on 11 benchmarks.

General frontier

23.9

#98 of 136 models · best at none

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. #226none of 58717.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #177none of 526-8.8

Leader: Opus 5.5 · 46.4

All 11 benchmarks

show 9 more

coding

Terminal-Bench v2.1-AA

238 results
  1. #100none of 23859.6%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #140none of 61027.3

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #129none of 2881123

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #238none of 52624.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #85none of 52656.3%

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

knowledge

GPQA Diamond

539 results
  1. #139none of 53984.5%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #178none of 26564.1%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #201none of 52371.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #308none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%