Skip to content

Qwen3 Integration #329

@kangqi-ni

Description

@kangqi-ni

I have attempted to reproduce Qwen/Qwen3-Coder-30B-A3B-Instruct 's performance on webarena and webarena-verified. However, using the Generic agent prompt, I achieved extremely low performance. Has anyone benchmarked Qwen/Qwen3-Coder-30B-A3B-Instruct on any of the benchmarks integrated here?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions