megatron-GPT-2-345m-EvolInstruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1123 ± 17, rank #10466 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 41.67 | Accuracy (%) | 60.7 |
| MMLU-by-task - High School Mathematics | 26.67 | Accuracy (%) | 45.9 |
| MMLU-by-task - TruthfulQA MC1 | 25.58 | Accuracy (%) | 36.4 |
| MMLU-by-task - TruthfulQA MC2 | 41.25 | Accuracy (%) | 32.3 |
| MMLU-by-task - Machine Learning | 28.57 | Accuracy (%) | 30.8 |
| MMLU-by-task - Jurisprudence | 29.63 | Accuracy (%) | 29.6 |
| MMLU-by-task - Formal Logic | 25.4 | Accuracy (%) | 28.9 |
| MMLU-by-task - High School Chemistry | 27.59 | Accuracy (%) | 27.4 |
| MMLU-by-task - High School European History | 27.27 | Accuracy (%) | 27.3 |
| MMLU-by-task - High School Government And Politics | 31.61 | Accuracy (%) | 26.2 |
| MMLU-by-task - Professional Medicine | 33.82 | Accuracy (%) | 26.2 |
| MMLU-by-task - Miscellaneous | 28.61 | Accuracy (%) | 25.7 |
Interactive version: theaggregate.ai/model?slug=megatron-gpt-2-345m-evolinstruct · How It Works · Data refreshed daily, snapshot 2026-11-08.