Qwen2.5 Coder 14B — Benchmarks

Benchmark scores for Qwen2.5 Coder 14B 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
HellaSwag80.2%#15 / 42#28 / 76
MMLU75.2%#19 / 76#44 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K88.7%#6 / 59#9 / 93

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