gemini-3-flash-preview
72±1
70interval74
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 3 min3 minutes ago
All sources syncing normally
- Arena · Text· 43 minutes ago
- Arena · WebDev· 43 minutes ago
- Arena · Vision· 43 minutes ago
- Arena · Agent· 43 minutes ago
- GPQA Diamond· 4 minutes ago
- SWE-bench· 3 minutes ago
- Terminal-Bench· 3 minutes ago
- ARC-AGI-2· 3 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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 27 | gemini-3-flash-preview | Google DeepMind | — | $0.50 / $3 | 72.3 78.4Ranked 72.3 = (11 × 78.4 + 3 × 50) ÷ 14. 78.4 is the mean percentile over the 11 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 70–74 | 82 | 11/22 | #27–99 | — | — | — | — | — | — | — | 79 | 82 | 81 | 88 | 55 | — | 75 | 89 | — | — | — | 99 | 100 | 97 | 18 |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model