Chatglm2 6B — Benchmarks

Benchmark scores for Chatglm2 6B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #55 of 73 open modelscomposite 34.2/100 across 4 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
HellaSwag57.0%#37 / 42#65 / 76
MMLU47.9%#60 / 76#111 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K32.4%#44 / 59#64 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard33.7%#33 / 37#46 / 50

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