gemini-2.5-pro-exp-03-25
60±1
58interval62
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 25 min25 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· 25 minutes ago
- SWE-bench· 25 minutes ago
- Terminal-Bench· 25 minutes ago
- ARC-AGI-2· 25 minutes ago
Filter by org:
Released:
gemini-2.5-pro-preview-03-25
60±0
59interval60
gemini-2.5-pro
58±2
56interval60
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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 143 | gemini-2.5-pro-exp-03-25 | Google DeepMind | — | — | 60.1 67.7Ranked 60.1 = (4 × 67.7 + 3 × 50) ÷ 7. 67.7 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 58–62 | 44 | 4/22 | #138–147 | — | — | — | — | — | — | — | 67 | — | — | — | — | 54 | 53 | 97 | — | — | — | — | — | — | — | ||
| 152 | gemini-2.5-pro-preview-03-25 | Google DeepMind | Mar 2025 | $1.25 / $10 | 59.7 74.4Ranked 59.7 = (2 × 74.4 + 3 × 50) ÷ 5. 74.4 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | 43 | 2/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 53 | 96 | — | — | — | — | — | — | — | ||
| 202 | gemini-2.5-pro | Jun 2025 | $1.25 / $10 | 57.7 59.5Ranked 57.7 = (13 × 59.5 + 3 × 50) ÷ 16. 59.5 is the mean percentile over the 13 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 56–60 | 87 | 13/22 | #60–432 | 81 | 8 | 68 | 78 | — | 13 | — | 69 | 61 | 51 | — | 35 | — | — | — | — | — | — | 95 | 90 | 55 | 70 | |||
| 283 | gemini-2.5-pro-06-05-highthinking | — | — | 54.8 69.1Ranked 54.8 = (1 × 69.1 + 3 × 50) ÷ 4. 69.1 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | — | 1/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 69 | — | — | — | — | — | — | — | |||
| 352 | gemini-2.5-pro-preview-06-05 | Google DeepMind | Jun 2025 | $1.25 / $10 | 52.2 53.5Ranked 52.2 = (5 × 53.5 + 3 × 50) ÷ 8. 53.5 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 50–53 | 68 | 5/22 | #137–352 | — | — | — | — | — | — | — | 68 | — | 48 | — | 11 | 61 | 79 | — | — | — | — | — | — | — | — | ||
| 424 | gemini-2.5-pro-preview-05-06 | Google DeepMind | May 2025 | $1.25 / $10 | 49.6 49.0Ranked 49.6 = (2 × 49.0 + 3 × 50) ÷ 5. 49.0 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 48–52 | 2 | 2/22low | #226–424 | — | — | — | — | — | — | — | 48 | — | — | — | — | 50 | — | — | — | — | — | — | — | — | — | ||
| 711 | gemini-2.5-pro-grounding | Jun 2025 | — | 41.7 16.7Ranked 41.7 = (1 × 16.7 + 3 × 50) ÷ 4. 16.7 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 40–42 | — | 1/22low | — | — | — | — | — | 17 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model