DeepSeek R1 Distill Qwen 14B — Benchmarks

Benchmark scores for DeepSeek R1 Distill Qwen 14B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Math

BenchmarkScoreRank
MATH Level 587.1%#4 / 23

Reasoning

BenchmarkScoreRank
GPQA Diamond44.7%#17 / 28

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