qwen3-4b
52.3%±3.0%
49.3%CI55.3%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 3 min3 minutes ago
All sources syncing normally
- Arena · Text· 6 hours ago
- Arena · WebDev· 6 hours ago
- Arena · Vision· 6 hours ago
- Arena · Agent· 6 hours ago
- GPQA Diamond· 3 minutes ago
- SWE-bench· 3 minutes ago
- Terminal-Bench· 3 minutes ago
- ARC-AGI-2· 3 minutes ago
Filter by org:
Released:
qwen3-4b-instruct-2507
45.8%±2.9%
43.0%CI48.7%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 141 | qwen3-4b | Alibaba | — | — | 52.3% | 49.3%–55.3% | #273–493 | ||
| 163 | qwen3-4b-instruct-2507 | — | — | — | 45.8% | 43.0%–48.7% | #338–592 |
Showing GPQA Diamond exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.