gemini-2.5-pro
14.1%±2.0%
12.1%CI16.2%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 26 min26 minutes ago
All sources syncing normally
- Arena · Text· 9 hours ago
- Arena · WebDev· 9 hours ago
- Arena · Vision· 9 hours ago
- Arena · Agent· 9 hours ago
- GPQA Diamond· 26 minutes ago
- SWE-bench· 26 minutes ago
- Terminal-Bench· 26 minutes ago
- ARC-AGI-2· 26 minutes ago
Filter by org:
Released:
gemini-2.5-pro-preview-06-05
10.3%±1.8%
8.6%CI12.1%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 35 | gemini-2.5-pro | Google DeepMind | Jun 2025 | $1.25 / $10 | 14.1% | 12.1%–16.2% | #60–432 | ||
| 37 | gemini-2.5-pro-preview-06-05 | Google DeepMind | Jun 2025 | $1.25 / $10 | 10.3% | 8.6%–12.1% | #137–352 |
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.