openthaigpt-1.0.0-alpha-7B-chat-ckpt-hf: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1252 ± 16, rank #9234 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 34 | Accuracy (%) | 82 |
| MMLU-by-task - Econometrics | 31.58 | Accuracy (%) | 73.2 |
| MMLU-by-task - Global Facts | 35 | Accuracy (%) | 64.2 |
| MMLU-by-task - TruthfulQA MC2 | 47.23 | Accuracy (%) | 61 |
| MMLU-by-task - TruthfulQA MC1 | 30.23 | Accuracy (%) | 58.7 |
| MMLU-by-task - Elementary Mathematics | 30.16 | Accuracy (%) | 57.8 |
| MMLU-by-task - Conceptual Physics | 40.85 | Accuracy (%) | 56.3 |
| MMLU-by-task - High School Geography | 59.6 | Accuracy (%) | 55.7 |
| MMLU-by-task - Astronomy | 45.39 | Accuracy (%) | 53.5 |
| MMLU-by-task - High School Chemistry | 34.48 | Accuracy (%) | 52.4 |
| MMLU-by-task - US Foreign Policy | 66 | Accuracy (%) | 49.4 |
| MMLU-by-task - Philosophy | 52.09 | Accuracy (%) | 47.5 |
Interactive version: theaggregate.ai/model?slug=openthaigpt-1-0-0-alpha-7b-chat-ckpt-hf · How It Works · Data refreshed daily, snapshot 2026-11-08.