priorsBuilder

Other · released 2026-02-10

Tri-21B-think Preview

Measured on 11 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. #399default of 5875.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #454default of 526-62.3

Leader: Opus 5.5 · 46.4

All 11 benchmarks

show 9 more

agentic

τ²-Bench Telecom

393 results
  1. #44default of 39393.3%

Leader: GLM 5.2 · 99.1%

coding

Terminal-Bench Hard-AA

387 results
  1. #305default of 3872.3%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #382default of 6109.6

Leader: Opus 5.5 · 57.6

instruction

IFBench

399 results
  1. #189default of 39947.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #465default of 52610.1%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #280default of 52619.5%

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

knowledge

GPQA Diamond

539 results
  1. #398default of 53953.8%

Leader: GPT-6 Astra · 96.3%

long-context

AA-LCR v1.1

523 results
  1. #405default of 52321.7%

Leader: Kimi K3 · 88.7%

reasoning

CritPt

529 results
  1. #390default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%