Internlm 20B — Benchmarks

Benchmark scores for Internlm 20B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #15 of 73 open modelscomposite 62.1/100 across 3 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
HellaSwag78.1%#16 / 42#33 / 76

Math

BenchmarkScoreOpen rankAll models
GSM8K62.9%#22 / 59#31 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard52.5%#18 / 37#25 / 50

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