Agentic Writing on DiscoX
75.8Pass@1Gemini 3-pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3-pro2026.03 | 75.8 | |
| GPT-5 High2026.03 | 75.1 | |
| Seed1.82026.03 | 74.6 | |
| Gemini 2.5-pro2026.03 | 73.5 | |
| Claude Sonnet-4.52026.03 | 71.6 |
| Method | Links | |
|---|---|---|
| Gemini 3-pro2026.03 | 75.8 | |
| GPT-5 High2026.03 | 75.1 | |
| Seed1.82026.03 | 74.6 | |
| Gemini 2.5-pro2026.03 | 73.5 | |
| Claude Sonnet-4.52026.03 | 71.6 |