DeepSeek V3.1 — Benchmarks

Benchmark scores for DeepSeek V3.1 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro84.8%#7 / 119#35 / 259

Reasoning

BenchmarkScoreOpen rankAll models
SimpleBench40.0%#10 / 19#61 / 90

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