Real World Tasks on ToB Compositional Tasks
64.8ScoreGemini-3-pro High
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-pro High2026.06 | 64.8 | |
| Claude-Opus-4.52026.06 | 63.6 | |
| Seed2.0 Pro2026.06 | 59.1 | |
| Gemini-3-Flash High2026.06 | 57.7 | |
| Claude-Sonnet-4.52026.06 | 57.3 | |
| Seed2.0 Lite2026.06 | 54.8 | |
| GPT-5.2 High2026.06 | 51.5 | |
| GPT-5-mini High2026.06 | 47.5 |