Closed gaotongxiao closed 1 year ago
Hi gaotong,
We've noticed that the Opencompass August LLM Leaderboard features an older version of our TigerBot model from June. We've released a new version in August and have also included its evaluation by opencompass in this project. Could you please update the leaderboard to reflect the results from our latest version of TigerBot?
@Vivicai1005 Sure, we will relaunch the evaluation and update the leaderboard asap. Thanks for your update.
Hi gaotong,
We've noticed that the evaluation results for Tigerbot model versions1 and 2 were mistakenly swapped on the Opencompass LLM Leaderboard. the current screenshot
the previous screenshots
Could you please update this?
Hi team,
Thanks for using OpenCompass! We're thrilled to see more LLM teams adopting the toolkit to evaluate models systematically. We deeply appreciate your dedication to transparency and reproducibility in LLM evaluation. Here we are wondering if you would add a badge to readme, with which visitors can quickly identify and appreciate the rigorous evaluation standards your model has undergone.
BTW, as OpenCompass continues to evolve, we welcome any evaluation requests or ideas for future collaborations. Feel free to let us know if your team needs any assistance.