Theory of Mind on ToMBench
81.8Accuracy
GPT-o3
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 81.8 | |
2026.02 | 80.3 | |
2026.02 | 80.1 | |
2026.02 | 79.7 | |
2026.02 | 77.5 | |
2026.02 | 76.3 | |
2026.02 | 75.4 | |
2026.02 | 72.9 | |
2026.02 | 67.4 |
GPT-o3
| Method | Links | |
|---|---|---|
2026.02 | 81.8 | |
2026.02 | 80.3 | |
2026.02 | 80.1 | |
2026.02 | 79.7 | |
2026.02 | 77.5 | |
2026.02 | 76.3 | |
2026.02 | 75.4 | |
2026.02 | 72.9 | |
2026.02 | 67.4 |