DeepSeek V2.5 — Benchmarks

Benchmark scores for DeepSeek V2.5 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Coding

BenchmarkScoreOpen rankAll models
Aider Polyglot17.8%#13 / 18#60 / 69

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro65.8%#41 / 119#117 / 259

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.