LLM data comprehension on Real-world data
74.3JSON Validity Rate
GPT-5.1-codex
Updated 11d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.04 | 74.3 | 71.4 | 2.9 | 35 | |
2026.04 | 71.4 | 62.9 | 8.6 | 35 | |
2026.04 | 71.4 | 71.4 | 0 | 35 | |
2026.04 | 68.6 | 68.6 | 0 | 35 | |
2026.04 | 62.9 | 68.6 | 5.7 | 35 | |
2026.04 | 60 | 57.1 | 2.9 | 35 | |
2026.04 | 59.1 | 59.4 | 0.3 | 350 | |
2026.04 | 54.3 | 54.3 | 0 | 35 | |
2026.04 | 45.7 | 48.6 | 2.9 | 35 | |
2026.04 | 42.9 | 45.7 | 2.9 | 35 | |
2026.04 | 40 | 45.7 | 5.7 | 35 |