deepseek-v3.1-terminus
67±0
66interval68
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 16 min16 minutes ago
All sources syncing normally
- Arena · Text· 55 minutes ago
- Arena · WebDev· 55 minutes ago
- Arena · Vision· 55 minutes ago
- Arena · Agent· 55 minutes ago
- GPQA Diamond· 16 minutes ago
- SWE-bench· 16 minutes ago
- Terminal-Bench· 16 minutes ago
- ARC-AGI-2· 16 minutes ago
Filter by org:
Released:
deepseek-v3.1-terminus-thinking
61±1
59interval62
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 | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 55 | deepseek-v3.1-terminus | deepseek | Sep 2025 | $0.27 / $1 | 67.2 77.6Ranked 67.2 = (5 × 77.6 + 3 × 50) ÷ 8. 77.6 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 66–68 | 26 | 5/22 | #55–168 | 68 | — | — | — | — | — | — | — | — | — | — | — | — | — | 72 | — | — | — | 92 | 90 | 66 | — | ||
| 132 | deepseek-v3.1-terminus-thinking | deepseek | Oct 2026 | — | 60.7 76.8Ranked 60.7 = (2 × 76.8 + 3 × 50) ÷ 5. 76.8 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 59–62 | 16 | 2/22low | #97–137 | 69 | — | — | — | — | — | — | — | — | — | — | — | — | — | 85 | — | — | — | — | — | — | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model