Internlm Chat 20B — Benchmarks

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

Overall rank: #56 of 73 open modelscomposite 33.8/100 across 3 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU57.4%#48 / 76#97 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K15.7%#54 / 59#78 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard42.4%#26 / 37#36 / 50

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