Coding Agent Capacity on ArtifactsBench
71.1Score
GPT-5.2 High
Updated 24d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 71.1 | |
2026.06 | 68.9 | |
2026.06 | 68.5 | |
2026.06 | 66.6 | |
2026.06 | 62.6 | |
2026.06 | 59.1 | |
2026.06 | 58.4 | |
2026.06 | 52.5 |
GPT-5.2 High
| Method | Links | |
|---|---|---|
2026.06 | 71.1 | |
2026.06 | 68.9 | |
2026.06 | 68.5 | |
2026.06 | 66.6 | |
2026.06 | 62.6 | |
2026.06 | 59.1 | |
2026.06 | 58.4 | |
2026.06 | 52.5 |