LongContext Understanding on DUDE (Pass@1)
72.4Pass@1Seed2.0 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Seed2.0 Pro2026.06 | 72.4 | |
| Seed2.0 Lite2026.06 | 72.1 | |
| Gemini-3-Pro High2026.06 | 70.1 | |
| Seed1.82026.06 | 69.4 | |
| Seed2.0 Mini2026.06 | 68.9 | |
| GPT-5.2 High2026.06 | 68.2 | |
| Claude-Opus-4.52026.06 | 55.6 |