Gemini 3.1 Pro (Preview) (High): benchmark results
Gemini 3.1 Pro (Preview) evaluated at the high reasoning-effort setting. Provider: Google. Released 2026-02-19. Access: API.
Aggregate Rating 1808 ± 5, rank #124 of 2168 rated models, from 429 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AGORA - Agriculture | 66.2 | Accuracy (%) on the 71 agriculture, resources and energy que | 100 |
| AGORA - Architecture | 68.97 | Accuracy (%) on the 29 architecture, construction, real esta | 100 |
| AGORA - Business | 72 | Accuracy (%) on the 50 business, management, marketing and s | 100 |
| AGORA - Education | 59.18 | Accuracy (%) on the 49 education, science and academia quest | 100 |
| AGORA - Healthcare | 64.71 | Accuracy (%) on the 34 healthcare and medicine questions (1, | 100 |
| Alem (Easy) | 18.1 | Total return (%): each agent's cumulative reward divided by | 100 |
| Alem (Easy) - Coordination | 18 | Coordination return (%): each agent's reward from coordinati | 100 |
| Alem (Hard) | 15.4 | Total return (%): each agent's cumulative reward divided by | 100 |
| Alem (Hard) - Coordination | 17.5 | Coordination return (%): each agent's reward from coordinati | 100 |
| Alem (Medium) | 18.6 | Total return (%): each agent's cumulative reward divided by | 100 |
| Alem (Medium) - Coordination | 23.4 | Coordination return (%): each agent's reward from coordinati | 100 |
| AudioMC | 66.8 | Score (imported) | 100 |
Interactive version: theaggregate.ai/model?slug=gemini-3-1-pro-preview-high · How It Works · Data refreshed daily, snapshot 2026-10-20.