Scientific Knowledge and Reasoning on SimpleQA Verified
72.1ScoreGemini-3-pro High
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-pro High2026.06 | 72.1 | |
| Gemini-3-FlashTier=High2026.06 | 65.4 | |
| Claude-Opus-4.52026.06 | 48.6 | |
| GPT-5.2 High2026.06 | 36.8 | |
| Seed2.0 Pro2026.06 | 36 | |
| Claude-Sonnet-4.52026.06 | 29.3 | |
| GPT-5-miniTier=High2026.06 | 26 | |
| Seed2.0 Lite2026.06 | 24 | |
| Seed2.0 Mini2026.06 | 18.9 |