List your company

Question Answering on BBQ Race

81.9AccuracyCatRAG
49.97258.26166.5574.839Mar 23, 2026

Evaluation results

MethodLinks
CatRAGBackbone=Gemma-32026.0381.90.01
CatRAGBackbone=GPT-OSS2026.0381.40.04
CausalBackbone=GPT-OSS2026.0381.30.06
CatRAGBackbone=Llama-32026.0380.70.01
CausalBackbone=Llama-32026.0379.80.1
CausalBackbone=Gemma-32026.03790.1
SPBackbone=GPT-OSS2026.0371.80.17
SPBackbone=Gemma-32026.0368.80.19
CEBackbone=GPT-OSS2026.0368.20.24
SPBackbone=Llama-32026.0367.40.21
CEBackbone=Gemma-32026.0365.20.27
CEBackbone=Llama-32026.0363.90.29
SelfBackbone=GPT-OSS2026.0362.90.37
SelfBackbone=Gemma-32026.03600.4
SelfBackbone=Llama-32026.0358.70.42
BaseBackbone=GPT-OSS2026.0355.40.56
BaseBackbone=Gemma-32026.0352.30.6
BaseBackbone=Llama-32026.0351.20.62