Qwen3 4B 2507 (Reasoning)
74.3%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 2 min2 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· 2 minutes ago
- ARC-AGI-2· 3 minutes ago
Filter by org:
Released:
Qwen3 4B (Reasoning)
69.6%
no interval published
Qwen3 4B 2507 Instruct
67.2%
no interval published
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 136 | Qwen3 4B 2507 (Reasoning) | alibaba | — | — | 74.3% | — | — | ||
| 162 | Qwen3 4B (Reasoning) | alibaba | — | — | 69.6% | — | #273–493 | ||
| 175 | Qwen3 4B 2507 Instruct | alibaba | — | — | 67.2% | — | — |
Showing MMLU-Pro (Artificial Analysis) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.