Multi-task Reasoning on BigBench Hard
31.1Score
GPT-4o
Updated 3mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.08 | 31.1 | 1 | |
2025.08 | 30.4 | 2 | |
2025.08 | 30.1 | 3 | |
2025.08 | 28.7 | 4 | |
2025.08 | 8.2 | 5 |
GPT-4o
| Method | Links | ||
|---|---|---|---|
2025.08 | 31.1 | 1 | |
2025.08 | 30.4 | 2 | |
2025.08 | 30.1 | 3 | |
2025.08 | 28.7 | 4 | |
2025.08 | 8.2 | 5 |