internlm-7B: benchmark results
Shanghai AI Lab's InternLM-7B, a base model pretrained on trillions of high-quality tokens, designed for practical use cases with a flexible toolset for building workflows. Provider: Shanghai AI Lab. Released 2023-07-06. Access: Open.
Aggregate Rating 1272 ± 30, rank #1517 of 1656 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ARC Challenge (AI2) | 69.5 | Accuracy (%) | 69.1 |
| Open Portuguese LLM - ENEM | 40.87 | Accuracy (%) | 30.3 |
| GSM8K | 31.2 | Accuracy (%) | 30.1 |
| T-Eval | 45.8 | Overall Score (%) | 30 |
| Open Portuguese LLM - OAB Exams | 32.98 | Accuracy (%) | 29.6 |
| PIQA | 77.9 | Accuracy (%) | 29.2 |
| Open Portuguese LLM - BLUEX | 33.52 | Accuracy (%) | 29.1 |
| HellaSwag | 70.6 | Accuracy (%) | 28.9 |
| C-Eval | 52.8 | Average (%) | 22.5 |
| MMLU | 51 | Accuracy (%) | 22.4 |
| Open Portuguese LLM - ASSIN2 RTE | 64.1 | Macro F1 (%) | 22.4 |
| Open Portuguese LLM - FaQuAD NLI | 43.97 | Macro F1 (%) | 17.1 |
Interactive version: theaggregate.ai/model?slug=internlm-7b · How It Works · Data refreshed daily, snapshot 2026-10-20.