priorsBuilder

Other · released 2026-09-03

K2 Horizon 3.7B

Measured on 16 benchmarks.

General frontier

18.8

#115 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. #256default of 58713.9%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #266default of 526-28.6

Leader: Opus 5.5 · 46.4

All 16 benchmarks

show 14 more

agentic

AA-Briefcase v1.1

224 results
  1. #151default of 224793

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #139default of 21914.7%

Leader: Gemini 4 · 77.5%

agentic

τ³-Banking

206 results
  1. #102default of 20619.6%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #218default of 22622.0%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #161default of 23828.1%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #171default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #273default of 61015.6

Leader: Opus 5.5 · 57.6

economics

GDP.pdf

210 results
  1. #175default of 2103.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #177default of 288882

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #460default of 52610.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #87default of 52655.9%

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

knowledge

GPQA Diamond

539 results
  1. #297default of 53969.2%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #262default of 52362.3%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #327default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%