priorsBuilder

Other · released 2025-12-11

Mi:dm K 2.5 Pro Preview

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. #327default of 5879.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #460default of 526-62.7

Leader: Opus 5.5 · 46.4

All 14 benchmarks

show 12 more

agentic

τ²-Bench Telecom

393 results
  1. #203default of 39349.4%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #110default of 28257.6%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #302default of 3873.0%

Leader: GPT-5.6 Sol · 65.9%

instruction

IFBench

399 results
  1. #203default of 39945.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #369default of 52616.4%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #492default of 5265.3%

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

knowledge

Global-MMLU-Lite

118 results
  1. #61default of 11881.4%

Leader: Gemini 3.1 Pro · 93.2%

knowledge

GPQA Diamond

539 results
  1. #274default of 53972.2%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #77default of 28581.3%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #435default of 52314.7%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #64default of 22878.7%

Leader: GPT-5.2 · 99.0%

reasoning

CritPt

529 results
  1. #528default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%