priorsBuilder

DeepSeek · released 2024-12-10

DeepSeek V2.5

Measured on 6 benchmarks.

General frontier

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

Your mix’s benchmarks

0 of 8 measured

This model has no results on your mix’s benchmarks.

All 6 benchmarks

show 6 more

composite

AA Intelligence Index v4.3.2

610 results
  1. #495none of 6106.6

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #170none of 2201323

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #169none of 2201323

Leader: Gemini 4 · 1553

knowledge

GPQA Diamond

539 results
  1. #452none of 53942.3%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #200none of 28566.6%

Leader: Gemini 3 Pro · 89.8%

math

MATH-500

162 results
  1. #101none of 16276.3%

Leader: GPT-5 · 99.4%