smaug-qwen2-72b-instruct
44±0
43interval44
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,308
- Last sync
- 23 min23 minutes ago
All sources syncing normally
- Arena · Text· 10 hours ago
- Arena · WebDev· 10 hours ago
- Arena · Vision· 10 hours ago
- Arena · Agent· 10 hours ago
- GPQA Diamond· 23 minutes ago
- SWE-bench· 23 minutes ago
- Terminal-Bench· 23 minutes ago
- ARC-AGI-2· 23 minutes ago
Filter by org:
Released:
lcb-math-qwen2-72b-instructv3-merged-50
44±0
43interval44
qwen2-72b-instruct
38±1
36interval38
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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 625 | smaug-qwen2-72b-instruct | abacusai | — | — | 43.9 25.4Ranked 43.9 = (1 × 25.4 + 3 × 50) ÷ 4. 25.4 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | — | 1/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 25 | — | — | — | — | — | — | — | ||
| 634 | lcb-math-qwen2-72b-instructv3-merged-50 | Alibaba | — | — | 43.6 24.4Ranked 43.6 = (1 × 24.4 + 3 × 50) ÷ 4. 24.4 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | — | 1/22low | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 24 | — | — | — | — | — | — | — | ||
| 899 | qwen2-72b-instruct | alibaba | Jun 2024 | — | 37.5 25.0Ranked 37.5 = (3 × 25.0 + 3 × 50) ÷ 6. 25.0 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 36–38 | 5 | 3/22 | #290–899 | 26 | — | — | — | — | — | — | 22 | — | — | — | — | — | — | 27 | — | — | — | — | — | — | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model