DeepSeek V3.2 Exp (Reasoning)
78.9%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 27 min27 minutes ago
All sources syncing normally
- Arena · Text· 48 minutes ago
- Arena · WebDev· 48 minutes ago
- Arena · Vision· 48 minutes ago
- Arena · Agent· 48 minutes ago
- GPQA Diamond· 27 minutes ago
- SWE-bench· 27 minutes ago
- Terminal-Bench· 27 minutes ago
- ARC-AGI-2· 27 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 | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 28 | DeepSeek V3.2 Exp (Reasoning) | deepseek | Sep 2025 | $0.27 / $0.41 | 78.9% | — | #92–334 |
Showing LiveCodeBench (Artificial Analysis) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.