priorsBuilder

Other · released 2025-12-15

K2 Think V2

Measured on 14 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #313high of 58710.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #312high of 526-40.3

Leader: Opus 5.5 · 46.4

All 14 benchmarks

show 12 more

agentic

AA-Briefcase v1.1

224 results
  1. #210high of 2247

Leader: Sonnet 5.5 · 1823

agentic

τ²-Bench Telecom

393 results
  1. #285high of 39325.4%

Leader: GLM 5.2 · 99.1%

coding

Terminal-Bench Hard-AA

387 results
  1. #244high of 3876.8%

Leader: GPT-5.6 Sol · 65.9%

coding

Terminal-Bench v2.1-AA

238 results
  1. #185high of 23815.0%

Leader: Fable 5.1 · 91.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #341high of 61011.5

Leader: Opus 5.5 · 57.6

economics

GDPval-AA v2.1

288 results
  1. #255high of 288130

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #116high of 39962.8%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #332high of 52618.0%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #220high of 52628.8%

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

knowledge

GPQA Diamond

539 results
  1. #281high of 53971.3%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #283high of 52357.0%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #361high of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%