internlm-7B: benchmark results
Provider: Shanghai AI Lab. Released 2023-07-06. Access: Open.
Unified ELO 1326 ± 1, rank #1312 of 1392 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ARC Challenge (AI2) | 69.5 | Accuracy (%) | 69.1 |
| PutnamBench | 4 | Problems Solved | 40.2 |
| GSM8K | 31.2 | Accuracy (%) | 30.1 |
| T-Eval | 45.8 | Overall Score (%) | 30 |
| PIQA | 77.9 | Accuracy (%) | 29.2 |
| HellaSwag | 70.6 | Accuracy (%) | 28.9 |
| MMLU | 51 | Accuracy (%) | 21.5 |
| Big-Bench Hard | 37 | Average (%) | 16.7 |
| BoolQ | 64.1 | Accuracy (%) | 15.6 |
| Epoch AI - Lambada | 67 | Score | 8 |
| InfiBench | 16.26 | Score (%) | 6.7 |
Interactive version: theaggregate.ai/model?slug=internlm-7b · How It Works · Data refreshed daily, snapshot 2026-09-05.