Lemur-70B-Chat-v1-GPTQ: benchmark results
Provider: Other.
Aggregate Rating 1391 ± 18, rank #6506 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Global Facts | 50 | Accuracy (%) | 98.8 |
| MMLU-by-task - College Physics | 41.18 | Accuracy (%) | 98.3 |
| MMLU-by-task - Computer Security | 78 | Accuracy (%) | 98 |
| MMLU-by-task - Elementary Mathematics | 46.03 | Accuracy (%) | 97.9 |
| MMLU-by-task - Security Studies | 79.18 | Accuracy (%) | 96.7 |
| MMLU-by-task - Formal Logic | 47.62 | Accuracy (%) | 96.4 |
| MMLU-by-task - TruthfulQA MC2 | 57.11 | Accuracy (%) | 95.6 |
| MMLU-by-task - Moral Scenarios | 50.73 | Accuracy (%) | 95.4 |
| MMLU-by-task - Econometrics | 42.98 | Accuracy (%) | 94.7 |
| MMLU-by-task - College Medicine | 63.58 | Accuracy (%) | 94.6 |
| MMLU-by-task - International Law | 84.3 | Accuracy (%) | 94.1 |
| MMLU-by-task - Logical Fallacies | 78.53 | Accuracy (%) | 93.5 |
Interactive version: theaggregate.ai/model?slug=lemur-70b-chat-v1-gptq · How It Works · Data refreshed daily, snapshot 2026-11-08.