Agentic benchmark
QwenWebBench leaderboard
Every model the catalog carries a published QwenWebBench value for, ranked by that value.
CategoryAgentic
MeasureElo-style artifact benchmark
TasksWeb artifacts and interactive deliverables
DifficultyArtifact generation
Published byQwen3.6 launch benchmarks
A Qwen benchmark for artifact and webpage generation quality reported as an Elo-style rating.
QwenWebBench ranking
5 models with a published QwenWebBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Elo-style artifact benchmark |
|---|---|---|---|
| 1 |  Qwen3.7 Max | Alibaba | 1568 |
| 2 | Qwen3.7 Plus | Alibaba | 1536 |
| 3 | Qwen 3.6 Max (preview) | Alibaba | 1532 |
| 4 | Qwen3.6-27B | Alibaba | 1487 |
| 5 | Qwen3.6-35B-A3B | Alibaba | 1397 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.