priorsBuilder

Other · released 2026-08-12

A.X-K2

Measured on 16 benchmarks.

General frontier

31.1

#79 of 135 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. #150default of 58729.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #174default of 526-8.2

Leader: Opus 5.5 · 46.4

All 16 benchmarks

show 14 more

agentic

AA-Briefcase v1.1

224 results
  1. #157default of 224737

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #173default of 2192.5%

Leader: Gemini 4 · 77.5%

agentic

τ³-Banking

206 results
  1. #113default of 20616.1%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #163default of 22641.0%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #142default of 23839.0%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #159default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #208default of 61021.5

Leader: Opus 5.5 · 57.6

economics

GDP.pdf

210 results
  1. #147default of 2106.4%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #168default of 288963

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #317default of 52618.6%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #55default of 52667.0%

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

knowledge

GPQA Diamond

539 results
  1. #122default of 53985.7%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #212default of 52370.0%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #125default of 5298.9%

Leader: Muse Wonder Full (Max) · 32.9%