List your company

Judge Performance Evaluation on SynJudge

0.54TCC (RMSE)QwenVL_trained
0.52120.64810.7750.9019Jun 11, 2025

Evaluation results

MethodLinks
QwenVL_trainedTraining Status=finetuned2025.060.540.720.680.6795.4
InternVL_trainedTraining Status=finetuned2025.060.550.70.720.7294.5
QwenVLTraining Status=zero-shot2025.060.811.090.961.287.5
InternVLTraining Status=zero-shot2025.060.960.91.061.0386.6
GPT-4oTraining Status=zero-shot2025.061.011.020.981.1886.5