Terry Yue Zhuo
Lead author of the BigCodeBench code-generation benchmark; former research lead at Alibaba Qwen
Terry Yue Zhuo is a researcher in code intelligence and frontier AI risks. Zhuo is first author of the BigCodeBench paper (2024), which introduced a benchmark for code generation with diverse function calls and complex instructions within the BigCode project. Zhuo's site says Zhuo was a research lead at Alibaba Qwen, where Zhuo founded the Qwen Cyber team, and earlier worked on code intelligence during a PhD at Monash University.12
Career
Zhuo worked on code intelligence during a PhD at Monash University and has spent time at Amazon AWS AI, ByteDance, Sea AI Lab and CSIRO's Data61. Zhuo later was a research lead at Alibaba Qwen, founding the Qwen Cyber team and leading training of language models with cyber capabilities. Zhuo's site lists current interests in frontier AI risks and dual-use capabilities.1
Research
Through the BigCode collaboration Zhuo was first author of BigCodeBench (2024), presented at ICLR 2025, and a co-author of StarCoder 2 (2024). Earlier single-author work includes ICE-Score (2023), on instructing LLMs to evaluate code, and later work includes Cyber-Zero (2025) and CTF-Dojo (2025), on training cybersecurity agents.213456
Work
BigCodeBenchOpen data
First author of "BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions" (2024), the paper that introduced the benchmark.21
StarCoder 2 and The Stack v2Open weights
Co-author of the StarCoder 2 and The Stack v2 paper (2024), which introduced the StarCoder2 models.3
Career timeline
Apr 2023
Posted "ICE-Score, Instructing Large Language Models to Evaluate Code" as sole author.4
Feb 2024
Co-authored the StarCoder 2 and The Stack v2 paper.3
Jun 2024
Posted the BigCodeBench paper as first author.2
Jul 2025
Posted "Cyber-Zero, Training Cybersecurity Agents without Runtime" as first author.5
Aug 2025
Posted "Training Language Model Agents to Find Vulnerabilities with CTF-Dojo" as first author.6
Other documented roles
Roles the sources document but that are not confirmed as current.
Honors and recognition
Related people
More sourced profiles at the same organization, in the same field, or from the same school.
- Harold BoothEvaluation and benchmarks
- Ajeya CotraEvaluation and benchmarks
- Andrew LaackDeveloper tools
- Aylin CaliskanSafety and alignment
- Beth BarnesEvaluation and benchmarks
- Collin BurnsSafety and alignment
- Dan HendrycksEvaluation and benchmarks
- David StutzSafety and alignment
- Diogo AlmeidaEvaluation and benchmarks
- Eric HorvitzEvaluation and benchmarks
- Eric Michael SmithSafety and alignment
- Ethan PerezSafety and alignment
Is this you?
Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction
Add this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/people/terry-yue-zhuo/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/people/terry-yue-zhuo/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Terry Yue Zhuo — Profile on USASI" height="20"></a>
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.