Functional Correctness on JSON-Bench
55.2Functional Accuracy @1
LAVE
Updated 3mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 55.2 | 55.5 | 56.6 | 56.7 | |
2026.01 | 55 | 56.1 | 56.3 | 56.4 | |
2026.01 | 54.4 | 54.7 | 55.1 | 55.5 | |
2026.01 | 54.1 | 54.5 | 54.7 | 54.7 | |
2026.01 | 53.7 | 54.1 | 54.1 | 54.1 | |
2026.01 | 53.1 | 53.3 | 53.6 | 53.6 | |
2026.01 | 53 | 54.7 | 55.3 | 55.3 | |
2026.01 | 52.9 | 53.1 | 53.3 | 53.5 | |
2026.01 | 52.9 | 53.1 | 53.2 | 53.2 | |
2026.01 | 52.1 | 52.9 | 53.3 | 53.7 | |
2026.01 | 52 | 52.9 | 53.3 | 53.7 | |
2026.01 | 51.5 | 53.3 | 53.5 | 53.9 | |
2026.01 | 50.6 | 51.8 | 52.2 | 52.5 | |
2026.01 | 49.8 | 50.4 | 50.7 | 50.7 | |
2026.01 | 46.9 | 48.8 | 49.2 | 49.6 | |
2026.01 | 45.5 | 46.2 | 46.5 | 46.7 |