Our new X account is live! Follow @wizwand_team for updates

Response Selection on PersonaMem

64.36Accuracy

TALLRec

Updated 4d ago

Evaluation Results

Method	Links
TALLRec 2026.01		64.36
GPT-OSS-20B 2026.01		61.74
DeepSeek-R1-671B 2026.01		61.44
Qwen3-8Bnon-thinking 2026.01		61.4
DeepSeek-R1-671B 2026.01		58.96
ALIGNXPLORE+ 2026.01		58.08
Qwen3-32Bthinking 2026.01		57.36
GPT-OSS-20B 2026.01		54.82
ALIGNXPLORE+ 2026.01		54.58
Qwen3-8Bthinking 2026.01		54.36
ALIGNXPLORE 2026.01		53.98
Qwen3-32Bthinking 2026.01		53.26
Qwen3-8Bthinking 2026.01		51.68
DS-R1-Distill-Qwen-7B 2026.01		49.28
ALIGNXPLORE 2026.01		48.42
DS-R1-Distill-Qwen-7B 2026.01		46.64