deepseek-v3.2-exp-thinking
59±3
55interval62
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 38 min38 minutes ago
All sources syncing normally
- Arena · Text· 6 hours ago
- Arena · WebDev· 6 hours ago
- Arena · Vision· 6 hours ago
- Arena · Agent· 6 hours ago
- GPQA Diamond· 38 minutes ago
- SWE-bench· 38 minutes ago
- Terminal-Bench· 38 minutes ago
- ARC-AGI-2· 38 minutes ago
Filter by org:
Released:
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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 180 | deepseek-v3.2-exp-thinking | deepseek | Oct 2026 | — | 58.6 67.1Ranked 58.6 = (3 × 67.1 + 3 × 50) ÷ 6. 67.1 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 55–62 | 12 | 3/22 | #77–180 | 72 | — | — | 60 | — | — | — | — | — | — | — | — | — | — | 68 | — | — | — | — | — | — | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model