Reference
Compare models
Select models and benchmarks. Scores are shown exactly within each benchmark’s own metric — never combined into an aggregate, average, or winner.
Models
1 selected
Qwen 3.6 Max PreviewAlibaba / Qwen
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | Qwen 3.6 Max PreviewAlibaba / Qwen |
|---|---|
| SWE-bench Verified% resolved | 76.7% |
| GPQA Diamondaccuracy | 89.1% |
SWE-bench Verified
% resolved
Qwen 3.6 Max Preview · Alibaba / Qwen
76.7%
GPQA Diamond
accuracy
Qwen 3.6 Max Preview · Alibaba / Qwen
89.1%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.