Gemini 3.1 Pro Preview
74±2
72interval77
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 17 min17 minutes ago
All sources syncing normally
- Arena · Text· 12 hours ago
- Arena · WebDev· 12 hours ago
- Arena · Vision· 12 hours ago
- Arena · Agent· 12 hours ago
- GPQA Diamond· 17 minutes ago
- SWE-bench· 17 minutes ago
- Terminal-Bench· 17 minutes ago
- ARC-AGI-2· 17 minutes ago
Filter by org:
Released:
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 21 | Gemini 3.1 Pro Preview | Sep 2026 | $2 / $12 | 74.2 78.8Ranked 74.2 = (16 × 78.8 + 3 × 50) ÷ 19. 78.8 is the mean percentile over the 16 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 72–77 | 70 | 16/22 | #9–36 | 96 | 54 | 85 | 87 | — | 42 | 27 | 97 | 82 | 83 | 96 | 83 | 96 | 98 | 96 | — | — | — | — | — | 95 | 43 |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model