deepseek-v3.2-exp-thinking
1,425±7
1,419CI1,432
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 35 min35 minutes ago
All sources syncing normally
- Arena · Text· 3 hours ago
- Arena · WebDev· 3 hours ago
- Arena · Vision· 3 hours ago
- Arena · Agent· 3 hours ago
- GPQA Diamond· 36 minutes ago
- SWE-bench· 35 minutes ago
- Terminal-Bench· 35 minutes ago
- ARC-AGI-2· 35 minutes ago
Filter by org:
Released:
deepseek-v3.2-exp
1,422±6
1,415CI1,428
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 110 | deepseek-v3.2-exp-thinking | deepseek | Oct 2026 | — | 1,425 | 1,419–1,432 | #77–181 | ||
| 117 | deepseek-v3.2-exp | deepseek | Sep 2025 | $0.27 / $0.41 | 1,422 | 1,415–1,428 | #92–334 |
Showing Overall exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.