o3-2025-04-16
6.5%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 10 min10 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· 10 minutes ago
- SWE-bench· 10 minutes ago
- Terminal-Bench· 10 minutes ago
- ARC-AGI-2· 10 minutes ago
Filter by org:
Released:
o3-pro-2025-06-10
4.9%
no interval published
o3-mini-2025-01-31
3.0%
no interval published
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 53 | o3-2025-04-16 | OpenAI | Apr 2025 | $2 / $8 | 6.5% | — | #79–318 | ||
| 62 | o3-pro-2025-06-10 | OpenAI | Jun 2025 | $20 / $80 | 4.9% | — | #282–897 | ||
| 66 | o3-mini-2025-01-31 | OpenAI | Jan 2025 | $1.10 / $4.40 | 3.0% | — | #127–388 |
Showing ARC-AGI-2 exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.