priorsBuilder

Other · released 2026-07-09

JT-4.1 Flash 236B A21B (Reasoning)

Measured on 13 benchmarks.

General frontier

43.2

#48 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. #54default of 58743.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #64default of 52620.6

Leader: Opus 5.5 · 46.4

All 13 benchmarks

show 11 more

agentic

AA-Briefcase v1.1

224 results
  1. #104default of 2241089

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #85default of 21946.5%

Leader: Gemini 4 · 77.5%

coding

SciCode

226 results
  1. #85default of 22652.0%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v4-AA

216 results
  1. #105default of 2163.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #95default of 61033.9

Leader: Opus 5.5 · 57.6

economics

GDP.pdf

210 results
  1. #137default of 2108.6%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #92default of 2881324

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #64default of 52649.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #144default of 52643.0%

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

long-context

AA-LCR v1.1

523 results
  1. #110default of 52378.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #95default of 52914.0%

Leader: Muse Wonder Full (Max) · 32.9%