List your company

Flight Recommendation Evaluation

0.52Inference Time per Round (s)Direct prompting
0.35561.46532.5753.6847Apr 5, 2026

Evaluation results

MethodLinks
Direct promptingBackbone=Gemma, Calls=1, Hardware=single A100 GPU2026.040.52
Direct promptingBackbone=Qwen, Calls=1, Hardware=single A100 GPU2026.040.63
Direct promptingBackbone=Llama, Calls=1, Hardware=single A100 GPU2026.040.74
Bayesian TeachingBackbone=Qwen, Calls=1, Hardware=single A100 GPU2026.041.05
Bayesian TeachingBackbone=Llama, Calls=1, Hardware=single A100 GPU2026.041.34
Bayesian TeachingBackbone=Gemma, Calls=1, Hardware=single A100 GPU2026.041.42
CoTBackbone=Gemma, Calls=1, Hardware=single A100 GPU2026.042.15
CoTBackbone=Qwen, Calls=1, Hardware=single A100 GPU2026.042.42
CoTBackbone=Llama, Calls=1, Hardware=single A100 GPU2026.042.87
Self-consistencyBackbone=Gemma, Calls=5, Hardware=single A100 GPU2026.043.67
Self-consistencyBackbone=Qwen, Calls=5, Hardware=single A100 GPU2026.043.68
Self-consistencyBackbone=Llama, Calls=5, Hardware=single A100 GPU2026.043.79
ADAPTFUSEBackbone=Gemma, Calls=5, Hardware=single A100 GPU2026.044.35
ADAPTFUSEBackbone=Qwen, Calls=5, Hardware=single A100 GPU2026.044.51
ADAPTFUSEBackbone=Llama, Calls=5, Hardware=single A100 GPU2026.044.63