Flight Recommendation on Flight Recommendation Final 5th Round
76.3AccuracyADAPTFUSE
Evaluation results
| Method | Links | |
|---|---|---|
| ADAPTFUSEBase Model=Llama 3 8B2026.04 | 76.3 | |
| ADAPTFUSEBase Model=Gemma 2 9B2026.04 | 76.2 | |
| Bayesian TeachingBase Model=Llama 3 8B2026.04 | 74.3 | |
| Bayesian TeachingBase Model=Gemma 2 9B2026.04 | 73.4 | |
| ADAPTFUSEBase Model=Qwen 2.5 7B2026.04 | 67.3 | |
| Bayesian TeachingBase Model=Qwen 2.5 7B2026.04 | 65.2 | |
| Oracle LearningBase Model=Gemma 2 9B2026.04 | 59.1 | |
| Oracle LearningBase Model=Llama 3 8B2026.04 | 58.3 | |
| Oracle LearningBase Model=Qwen 2.5 7B2026.04 | 51.7 | |
| Self-consistencyBase Model=Gemma 2 9B, N=52026.04 | 44.7 | |
| Self-consistencyBase Model=Llama 3 8B, N=52026.04 | 43.8 | |
| Self-consistencyBase Model=Qwen 2.5 7B, N=52026.04 | 41.5 | |
| CoTBase Model=Llama 3 8B2026.04 | 39.1 | |
| CoTBase Model=Qwen 2.5 7B2026.04 | 38.6 | |
| CoTBase Model=Gemma 2 9B2026.04 | 38.4 | |
| Direct PromptingBase Model=Llama 3 8B2026.04 | 34.6 | |
| Direct PromptingBase Model=Qwen 2.5 7B2026.04 | 34.1 | |
| Direct PromptingBase Model=Gemma 2 9B2026.04 | 33.5 |