Agentic Coding on U-Artifacts
57.8Pass@1Gemini 3-pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3-pro2026.03 | 57.8 | |
| GPT-5 High2026.03 | 56.8 | |
| Seed1.82026.03 | 49.2 | |
| Claude Sonnet-4.52026.03 | 37.3 | |
| Gemini 2.5-pro2026.03 | 33.4 |
| Method | Links | |
|---|---|---|
| Gemini 3-pro2026.03 | 57.8 | |
| GPT-5 High2026.03 | 56.8 | |
| Seed1.82026.03 | 49.2 | |
| Claude Sonnet-4.52026.03 | 37.3 | |
| Gemini 2.5-pro2026.03 | 33.4 |