List your company

Empathetic Dialogue on Chit Chat

83.3ScoreGemini2.5-Pro-0605
35.9848.26560.5572.835Jul 3, 2025

Evaluation results

MethodLinks
Gemini2.5-Pro-06052025.0783.37711
OpenAI-o3-04162025.0783669
GPT-4o-03262025.0780.97417
GPT-4.1-04142025.0777.16518
Gemini2.5-Flash-Think-05202025.0764.75327
RLVER (PPO)Think=Yes2025.0762.15230
RLVER (PPO)Think=No2025.0753.43937
RLVER (GRPO)Think=Yes2025.07534542
RLVER (GRPO)Think=No2025.0749.23440
Qwen2.5-7B-Instruct2025.0737.82758