deepseek-v3.1-terminus-thinking
1,416±10
1,406CI1,426
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 18 min18 minutes ago
All sources syncing normally
- Arena · Text· 11 hours ago
- Arena · WebDev· 11 hours ago
- Arena · Vision· 11 hours ago
- Arena · Agent· 11 hours ago
- GPQA Diamond· 18 minutes ago
- SWE-bench· 18 minutes ago
- Terminal-Bench· 18 minutes ago
- ARC-AGI-2· 18 minutes ago
Filter by org:
Released:
deepseek-v3.1-terminus
1,415±10
1,405CI1,424
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 125 | deepseek-v3.1-terminus-thinking | deepseek | Oct 2026 | — | 1,416 | 1,406–1,426 | #97–137 | ||
| 129 | deepseek-v3.1-terminus | deepseek | Sep 2025 | $0.27 / $1 | 1,415 | 1,405–1,424 | #55–168 |
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.