Qwen3: benchmark results
Provider: Alibaba.
Aggregate Rating 1677 ± 45, rank #462 of 10916 rated models, from 4 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PHYBench | 40.76 | EED Score | 64.5 |
| Spider 2.0-Lite | 44.5 | Accuracy (%) | 52.9 |
| RPC-Bench | 56.26 | F1-like (%) | 30.8 |
| Are Agents Ready to Teach? A Multi-Stage Bench | 42.9 | Eq. pass (self-reported) | 10 |
Interactive version: theaggregate.ai/model?slug=qwen3 · How It Works · Data refreshed daily, snapshot 2026-11-08.