Qwen3 30B A3B 2507 (Reasoning)
80.5%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 37 min37 minutes ago
All sources syncing normally
- Arena · Text· 7 hours ago
- Arena · WebDev· 7 hours ago
- Arena · Vision· 7 hours ago
- Arena · Agent· 7 hours ago
- GPQA Diamond· 37 minutes ago
- SWE-bench· 37 minutes ago
- Terminal-Bench· 37 minutes ago
- ARC-AGI-2· 37 minutes ago
Filter by org:
Released:
Qwen3 30B A3B (Reasoning)
77.7%
no interval published
Qwen3 30B A3B 2507 Instruct
77.7%
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 85 | Qwen3 30B A3B 2507 (Reasoning) | alibaba | — | — | 80.5% | — | — | ||
| 112 | Qwen3 30B A3B (Reasoning) | alibaba | Apr 2025 | $0.12 / $0.50 | 77.7% | — | #187–454 | ||
| 113 | Qwen3 30B A3B 2507 Instruct | alibaba | — | — | 77.7% | — | — |
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.