gpt-5.2-search
1,161±6
1,156CI1,167
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 12 min12 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· 12 minutes ago
- SWE-bench· 12 minutes ago
- Terminal-Bench· 12 minutes ago
- ARC-AGI-2· 12 minutes ago
Filter by org:
Released:
gpt-5.2-search-non-reasoning
1,136±6
1,130CI1,142
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 33 | gpt-5.2-search | openai | Oct 2026 | — | 1,161 | 1,156–1,167 | — | ||
| 39 | gpt-5.2-search-non-reasoning | openai | Oct 2026 | — | 1,136 | 1,130–1,142 | — |
Showing Search Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.