Qwen 3 4B (baseline): benchmark results
Provider: Alibaba.
Aggregate Rating 1502 ± 50, rank #2327 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| STT-Arena - Easy | 18.31 | Pass@1 (%) on the 71 easy tasks (a single isolated conflict | 10 |
| STT-Arena - Impossible | 10 | Pass@1 (%) on the 30 impossible tasks (no valid completion p | 9.5 |
| STT-Arena | 10.57 | Overall (self-reported) | 5 |
| STT-Arena - Medium | 9.46 | Pass@1 (%) on the 67 medium tasks; a task passes when every | 5 |
| STT-Arena - Hard | 2.82 | Pass@1 (%) on the 59 hard tasks (long-horizon cascading cons | 2.5 |
Interactive version: theaggregate.ai/model?slug=qwen-3-4b-baseline · How It Works · Data refreshed daily, snapshot 2026-11-08.