priorsBuilder

Other · released 2026-09-03

K2 Horizon 7B

Measured on 16 benchmarks.

General frontier

22.1

#102 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. #225default of 58718.2%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #222default of 526-16.6

Leader: Opus 5.5 · 46.4

All 16 benchmarks

show 14 more

agentic

AA-Briefcase v1.1

224 results
  1. #114default of 2241016

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #130default of 21920.9%

Leader: Gemini 4 · 77.5%

agentic

τ³-Banking

206 results
  1. #75default of 20627.6%

Leader: Qwen 3.8 Max · 51.3%

coding

SciCode

226 results
  1. #210default of 22627.5%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #132default of 23844.2%

Leader: Fable 5.1 · 91.4%

coding

Terminal-Bench v4-AA

216 results
  1. #133default of 2161.0%

Leader: Sonnet 5.5 · 63.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #221default of 61020.6

Leader: Opus 5.5 · 57.6

economics

GDP.pdf

210 results
  1. #174default of 2103.2%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #154default of 2881023

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #440default of 52612.8%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #57default of 52666.4%

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

knowledge

GPQA Diamond

539 results
  1. #243default of 53975.3%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #217default of 52369.7%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #268default of 5290.3%

Leader: Muse Wonder Full (Max) · 32.9%