DeepSeek V4.1 Flash 1017
99.4%99.1%–99.8%
99.1%CI99.8%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 37,657
- Last sync
- 5 min5 minutes ago
All sources syncing normally
- Arena · Text· 1 hour ago
- Arena · WebDev· 1 hour ago
- Arena · Vision· 1 hour ago
- Arena · Agent· 1 hour ago
- GPQA Diamond· 5 minutes ago
- SWE-bench· 5 minutes ago
- Terminal-Bench· 5 minutes ago
- ARC-AGI-2· 5 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.
76 models that are not available today are left out of this ranking.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 13 | DeepSeek V4.1 Flash 1017 | DeepSeek | Oct 2026 | $0.15 / $0.60 | 99.4% | 99.1%–99.8% | #19–158 |
Showing AIME (math) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.