gemini-3-flash-preview
35.6%±2.8%
32.8%CI38.5%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 32 min32 minutes ago
All sources syncing normally
- Arena · Text· 53 minutes ago
- Arena · WebDev· 53 minutes ago
- Arena · Vision· 53 minutes ago
- Arena · Agent· 53 minutes ago
- GPQA Diamond· 32 minutes ago
- SWE-bench· 32 minutes ago
- Terminal-Bench· 32 minutes ago
- ARC-AGI-2· 32 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 | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 14 | gemini-3-flash-preview | Google DeepMind | — | $0.50 / $3 | 35.6% | 32.8%–38.5% | #27–99 |
Showing FrontierMath exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.