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.

No overall rank for Yi 6B: an overall score is only published when a model has been measured on enough of the benchmarks current models are still submitted to. Its individual scores below stand on their own — see the methodology for how the overall score is built.

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro26.5%#123 / 144#230 / 257
ARC Challenge50.3%#31 / 56#48 / 76
MMLU64.0%#41 / 85#81 / 136
HellaSwag74.4%#25 / 47#45 / 75

Math

BenchmarkScoreOpen rankAll models
GSM8K32.5%#45 / 62#63 / 93

Reasoning

BenchmarkScoreOpen rankAll models
WinoGrande71.3%#24 / 51#46 / 79
BIG-Bench Hard42.8%#26 / 38#35 / 50

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

Yi 6B Benchmarks — Scores & Rankings | llmrun