Real World Tasks on ToB
69ScoreSeed2.0 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed2.0 Pro2026.06 | 69 | |
| Gemini-3-pro High2026.06 | 67.5 | |
| Seed2.0 Lite2026.06 | 64.5 | |
| Claude-Sonnet-4.52026.06 | 64.5 | |
| Claude-Opus-4.52026.06 | 63.9 | |
| GPT-5.2 High2026.06 | 62.1 | |
| Gemini-3-Flash High2026.06 | 61.9 | |
| GPT-5-mini High2026.06 | 52.7 | |
| Seed2.0 Pro2026.06 | 52 | |
| Claude-Opus-4.52026.06 | 50.1 | |
| Gemini-3-pro High2026.06 | 49 | |
| Seed2.0 Lite2026.06 | 48.4 | |
| Claude-Sonnet-4.52026.06 | 48.3 | |
| Gemini-3-Flash High2026.06 | 45.4 | |
| GPT-5.2 High2026.06 | 44.7 | |
| GPT-5-mini High2026.06 | 40.5 |