DeepSeek V3.1 (Reasoning)
85.1%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 11 min11 minutes ago
All sources syncing normally
- Arena · Text· 9 hours ago
- Arena · WebDev· 9 hours ago
- Arena · Vision· 9 hours ago
- Arena · Agent· 9 hours ago
- GPQA Diamond· 11 minutes ago
- SWE-bench· 11 minutes ago
- Terminal-Bench· 11 minutes ago
- ARC-AGI-2· 11 minutes ago
Filter by org:
Released:
DeepSeek V3.1 Terminus (Reasoning)
85.1%
no interval published
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 22 | DeepSeek V3.1 (Reasoning) | deepseek | Aug 2025 | — | 85.1% | — | #101–158 | ||
| 23 | DeepSeek V3.1 Terminus (Reasoning) | deepseek | Sep 2025 | $0.27 / $1 | 85.1% | — | #54–168 |
Showing MMLU-Pro (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.