deepseek-v4-pro-0813
91.7%±1.5%
90.1%CI93.2%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 25 min25 minutes ago
All sources syncing normally
- Arena · Text· 5 hours ago
- Arena · WebDev· 5 hours ago
- Arena · Vision· 5 hours ago
- Arena · Agent· 5 hours ago
- GPQA Diamond· 25 minutes ago
- SWE-bench· 25 minutes ago
- Terminal-Bench· 25 minutes ago
- ARC-AGI-2· 25 minutes ago
Filter by org:
Released:
deepseek-v4-pro
90.9%±2.0%
88.9%CI93.0%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 26 | deepseek-v4-pro-0813 | DeepSeek | Aug 2026 | $0.66 / $1.98 | 91.7% | 90.1%–93.2% | #40–130 | ||
| 31 | deepseek-v4-pro | DeepSeek | Aug 2026 | $0.66 / $1.98 | 90.9% | 88.9%–93.0% | #17–54 |
Showing GPQA Diamond exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.