List your company

Response Quality Evaluation on Controversial Topics (test)

1.17Win ScoreDEBATUNE-13B
-0.01560.29220.60.9078Feb 16, 2024

Evaluation results

MethodLinks
DEBATUNE-13BParameters=13B2024.021.174310116
DEBATUNE-7BParameters=7B, Role=baseline2024.021———
WizardLM 13B V1.2Parameters=13B, Version=V1.22024.020.79149947
Zephyr 7B BetaParameters=7B, Version=Beta2024.020.67128464
Vicuna 13B v1.5Parameters=13B, Version=v1.52024.020.29536119
Zephyr 7B AlphaParameters=7B, Version=Alpha2024.020.27729124
LLaMA2 Chat 13BParameters=13B2024.020.2326131
Vicuna 7B v1.5Parameters=7B, Version=v1.52024.020.19619135
LLaMA2 Chat 7BParameters=7B2024.020.12117142
WizardLM 7BParameters=7B2024.020.11312145
Alpaca 7BParameters=7B2024.020.0321157