gpt-5.2-chat-latest-20260210
1,451±4
1,447CI1,454
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 21 min21 minutes ago
All sources syncing normally
- Arena · Text· 12 hours ago
- Arena · WebDev· 12 hours ago
- Arena · Vision· 12 hours ago
- Arena · Agent· 12 hours ago
- GPQA Diamond· 21 minutes ago
- SWE-bench· 21 minutes ago
- Terminal-Bench· 21 minutes ago
- ARC-AGI-2· 21 minutes ago
Filter by org:
Released:
gpt-5.2
1,442±3
1,439CI1,445
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 60 | gpt-5.2-chat-latest-20260210 | openai | Feb 2026 | — | 1,451 | 1,447–1,454 | #44–72 | ||
| 80 | gpt-5.2 | openai | Dec 2025 | $1.75 / $14 | 1,442 | 1,439–1,445 | #34–92 |
Showing Factuality Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.