Qwen3 4B 2507 (Reasoning)
54±0
53interval54
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 52 min52 minutes ago
All sources syncing normally
- Arena · Text· 4 hours ago
- Arena · WebDev· 4 hours ago
- Arena · Vision· 4 hours ago
- Arena · Agent· 4 hours ago
- GPQA Diamond· 52 minutes ago
- SWE-bench· 52 minutes ago
- Terminal-Bench· 52 minutes ago
- ARC-AGI-2· 52 minutes ago
Filter by org:
Released:
qwen3-4b
48±0
47interval49
qwen3-4b-instruct-2507
45±1
43interval47
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 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 307 | Qwen3 4B 2507 (Reasoning) | alibaba | — | — | 54.0 58.0Ranked 54.0 = (3 × 58.0 + 3 × 50) ÷ 6. 58.0 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | 19 | 3/22 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 49 | 68 | 56 | — | ||
| 493 | qwen3-4b | Alibaba | — | — | 47.9 46.6Ranked 47.9 = (5 × 46.6 + 3 × 50) ÷ 8. 46.6 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 47–49 | 58 | 5/22 | #273–493 | — | — | — | — | — | — | — | 37 | — | — | — | — | — | — | — | — | — | — | 40 | 54 | 22 | 80 | ||
| 592 | qwen3-4b-instruct-2507 | qwen | — | — | 44.7 39.4Ranked 44.7 = (3 × 39.4 + 3 × 50) ÷ 6. 39.4 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 43–47 | 26 | 3/22 | #338–592 | — | — | — | — | — | — | — | 27 | 39 | — | — | — | — | — | — | 52 | — | — | — | — | — | — | ||
| 660 | Qwen3 4B 2507 Instruct | alibaba | — | — | 42.9 35.7Ranked 42.9 = (3 × 35.7 + 3 × 50) ÷ 6. 35.7 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | — | 22 | 3/22 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 35 | 47 | 25 | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model