Alibaba · tested in Taskade Genesis
Qwen 3.7 Max in Taskade
Qwen 3.7 Max from Alibaba runs on the Max and Enterprise plans. We last tested it on Aug 25, 2026 in TSK-1, our app-building test.
- Status
- Available
- Plan
- Max and Enterprise
- Where to pick it
- More models or All Models
- Your own key
- No
- Last test
- Context window
- 1Mtokens
- Max output
- 131Ktokens
- Released
- Where it runs
- 5services
TSK-1 scorecard for the Qwen family
TSK Score
Qwen family, across real apps made in Taskade Genesis
- Interfaceready to share
- Emerging
- Taskcompletes your task
- Strong
- Memorykeeps your data
- Emerging
- Adapthandles follow-up edits
- Limited
A clean, complete match tracker on its first run.
MoreLess
One rough edge: with no hero picked, the save button did nothing and said nothing.
Published scores
Benchmark scores that Alibaba and test sites published for Qwen 3.7 Max. Taskade did not re-run them. Lab-reported marks a score from Alibaba itself.
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Verifiedresolved · QwenLab-reported | 80.4% | QwenLab-reported |
| SWE-Bench Proresolve rate · QwenLab-reported | 60.6% | QwenLab-reported |
| Terminal-Benchsuccess rate · v2.0 · Terminus-2 · QwenLab-reported | 69.7% | QwenLab-reported |
| MCP Atlassuccess rate · QwenLab-reported | 76.4% | QwenLab-reported |
| GPQA Diamondaccuracy · QwenLab-reported | 92.4% | QwenLab-reported |
| Humanity's Last Examaccuracy · QwenLab-reported | 41.4% | QwenLab-reported |
More published scores (3)
LMArena scores
| Benchmark | Score | Source |
|---|---|---|
| WebDev arena±7 · 8,881 votes · Rank 55 of 145 · LMArena | 1,516 | LMArena |
Scores from the LMArena leaderboard dataset (CC BY 4.0). People vote between two answers, and the votes set the score. Taskade picked the Overall category and the default setting of each model.
Scores collected by models.dev (MIT). Each source links the page that published the score.
Versions tested
Open a version to read its findings.
Qwen 3.7 MaxTested Aug 20262 findings
A clean, complete match tracker on its first run. One rough edge: with no hero picked, the save button did nothing and said nothing.
Complete match tracker with a clean dashboard on the first run; it saved a real match once a hero was picked.
With the hero left blank, the save button did nothing and said nothing: a first-use trap for a real user.
Model facts
The token limits are the most the model accepts. Taskade can run it with lower limits.
- Last updated
- Input types
- Text
- Output types
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- File attachments
- No
- Open weights
- No
Published specs from the model maker, via models.dev (MIT).
Where it runs
Services outside Taskade that serve Qwen 3.7 Max, from models.dev. Each link opens in a new tab.
How to choose Qwen 3.7 Max
- In the builder chat, open the model menu and choose More models. Then pick the model.
- In the agent editor, pick the model under All Models.
- If your model menu does not show the model, Taskade uses TSK-Auto instead.
Where Qwen ranks
TSK Score out of 100.
Compare Qwen
Other Alibaba models
FAQ
Which Taskade plans include Qwen 3.7 Max?
Qwen 3.7 Max runs in Taskade on the Max and Enterprise plans. If your model menu does not show it, Taskade uses TSK-Auto instead.
Has Taskade tested Qwen 3.7 Max?
Yes. We last tested Qwen 3.7 Max on Aug 25, 2026 in the TSK-1 Benchmark. A clean, complete match tracker on its first run. One rough edge: with no hero picked, the save button did nothing and said nothing.
How do I choose Qwen 3.7 Max in Taskade?
In the builder chat, open the model menu and choose More models. Then pick Qwen 3.7 Max. In the agent editor, pick it under All Models.
Who makes Qwen 3.7 Max?
Alibaba makes Qwen 3.7 Max. Taskade runs it on the Max and Enterprise plans, beside frontier models from other top AI labs.