Yi 6B — Benchmarks

Benchmark scores for Yi 6B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #46 of 73 open modelscomposite 40.2/100 across 5 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
HellaSwag74.4%#24 / 42#45 / 76
MMLU-Pro26.5%#101 / 119#232 / 259
MMLU64.0%#37 / 76#81 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K32.5%#43 / 59#63 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard42.8%#25 / 37#35 / 50

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