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
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU | 57.4% | #48 / 76 | #97 / 136 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GSM8K | 15.7% | #54 / 59 | #78 / 93 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| BIG-Bench Hard | 42.4% | #26 / 37 | #36 / 50 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.