List your company

Question Answering on BBQ Gender

82.4AccuracyCausal
40.48851.36962.2573.131Mar 23, 2026

Evaluation results

MethodLinks
CausalBackbone=GPT-OSS2026.0382.40.04
CatRAGBackbone=GPT-OSS2026.0382.20.04
CausalBackbone=GPT-OSS2026.03820.03
CatRAGBackbone=Gemma-32026.0381.60.03
CatRAGBackbone=Llama-32026.0381.20.01
CatRAGBackbone=GPT-OSS2026.0381.20.06
CatRAGBackbone=Gemma-32026.0380.70.02
CatRAGBackbone=Llama-32026.0379.50.02
CausalBackbone=Gemma-32026.0379.30.1
CausalBackbone=Llama-32026.0378.10.1
CausalBackbone=Llama-32026.03780.1
CausalBackbone=Gemma-32026.0376.40.09
SPBackbone=GPT-OSS2026.0375.60.12
SPBackbone=Gemma-32026.0372.60.14
CEBackbone=GPT-OSS2026.03720.2
SPBackbone=Llama-32026.0371.20.16
SPBackbone=GPT-OSS2026.03700.19
CEBackbone=Gemma-32026.0369.10.23
CEBackbone=Llama-32026.0367.80.25
SPBackbone=Gemma-32026.03670.21
SelfBackbone=GPT-OSS2026.0366.90.32
SPBackbone=Llama-32026.0365.60.23
CEBackbone=GPT-OSS2026.0364.20.3
SelfBackbone=Gemma-32026.0363.70.36
SelfBackbone=Llama-32026.0362.40.38
SelfBackbone=GPT-OSS2026.03620.39
CEBackbone=Gemma-32026.0361.20.33
CEBackbone=Llama-32026.0359.80.35
SelfBackbone=Gemma-32026.0359.30.43
SelfBackbone=Llama-32026.0357.90.45
BaseBackbone=GPT-OSS2026.0356.80.52
BaseBackbone=Gemma-32026.0353.60.57
BaseBackbone=Llama-32026.0352.30.59
BaseBackbone=GPT-OSS2026.0346.80.64
BaseBackbone=Gemma-32026.0343.50.69
BaseBackbone=Llama-32026.0342.10.71