gemini-2.5-flash-preview-09-2025
1,229±10
1,219CI1,239
aiqbench · LLM benchmarks
1,229±10
1,219CI1,239
1,215±5
1,211CI1,220
1,188±7
1,181CI1,196
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 64 | gemini-2.5-flash-preview-09-2025 | Sep 2025 | — | 1,229 | 1,219–1,239 | #141–383 | |||
| 72 | gemini-2.5-flash | Jun 2025 | $0.30 / $2.50 | 1,215 | 1,211–1,220 | #133–389 | |||
| 88 | gemini-2.5-flash-lite-preview-06-17-thinking | Jan 2026 | — | 1,188 | 1,181–1,196 | #159–426 | |||
| 93 | gemini-2.5-flash-lite-preview-09-2025-no-thinking | Sep 2025 | — | 1,175 | 1,165–1,184 | #170–613 |
Showing Vision Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.