New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Tongyi DeepResearch
About Tongyi DeepResearch
Tongyi DeepResearch is an AI model developed by Alibaba-NLP, in the language category, released in 2025, made available as an open-weights model with 30.5B params.
On this page you'll find Tongyi DeepResearch's full specifications, including 13 benchmark results. Review provider pricing and benchmark scores below, or compare Tongyi DeepResearch head-to-head with other language models.
Links
Run Tongyi DeepResearch locally — what to buy
Share this build ↗Sized to what Tongyi DeepResearch actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.
Software support
✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.
Community
No reports yet. Own this model on some hardware? Be the first to confirm it runs.
No comments yet. Start the discussion.
Tongyi DeepResearch benchmark scores▶
| Benchmark | Category | Score | Variant |
|---|---|---|---|
| BrowseComp | agentic | 58.3% | heavy-mode |
| BrowseComp | agentic | 43.4% | react-avg@3 |
| BrowseComp-Zh | agentic | 58.1 | heavy-mode |
| BrowseComp-Zh | agentic | 46.7 | react-avg@3 |
| GAIA | agentic | 70.9 | react-avg@3 |
| WebWalkerQA | agentic | 72.2 | react-avg@3 |
| xbench-DeepSearch | agentic | 75 | react-avg@3 |
| Frames | long-context | 90.6 | react-avg@3 |
| AIME 2025 | math | 100% | with-search-and-python |
| HMMT 2025 (combined) | math | 100 | with-search-and-python |
| Humanity's Last Exam | reasoning | 38.3% | heavy-mode |
| Humanity's Last Exam | reasoning | 32.9% | react-avg@3 |
| SimpleQA | safety | 98.6% | with-search |
More models like Tongyi DeepResearch
Frequently asked questions
What is Tongyi DeepResearch? ▶
Tongyi DeepResearch is an AI model developed by Alibaba-NLP, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.
Who created Tongyi DeepResearch? ▶
Tongyi DeepResearch was developed by Alibaba-NLP and released in 2025.
Is Tongyi DeepResearch open source or proprietary? ▶
Tongyi DeepResearch ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.
How much does Tongyi DeepResearch cost? ▶
Pricing for Tongyi DeepResearch depends on the provider. See the providers table on this page for the latest API rates.
How does Tongyi DeepResearch perform on benchmarks? ▶
Tongyi DeepResearch is benchmarked across 13 evaluations on GenAIList, including BrowseComp (58.3%). See the full benchmark table below and compare it with other models.
Know a great video about Tongyi DeepResearch?
Add YouTube Video
Add Tweet/Discussion
Report an Issue
Help us maintain accurate information in our database.
Suggest an Edit
Tell us what needs to be changed or corrected for