Benchmark results | 是否有基准测试结果 (HLE, Browsecomp...etc)? #12
Description
Hey Minimax team, thank you so much for open-sourcing Mini-Agent! Curious if there are any performance benchmarks for Mini-Agent (HLE, Browsecomp...etc) or if there are plans to benchmark it in the future?
Thanks again for your great work! 🙏
你好，Minimax 团队，非常感谢你们开源 Mini-Agent！想请问目前是否有 Mini-Agent 的性能基准测试（如 HLE、Browsecomp 等），或者未来是否有计划进行相关的基准测试？
再次感谢你们的卓越工作！🙏