Flight Recommendation on Flight Recommendation 1st Round
55.5AccuracyBayesian Teaching
Evaluation Results
| Method | Links | |
|---|---|---|
| Bayesian TeachingBase Model=Llama 3 8B2026.04 | 55.5 | |
| Bayesian TeachingBase Model=Gemma 2 9B2026.04 | 54.1 | |
| ADAPTFUSEBase Model=Gemma 2 9B2026.04 | 53.1 | |
| Bayesian TeachingBase Model=Qwen 2.5 7B2026.04 | 52.5 | |
| ADAPTFUSEBase Model=Llama 3 8B2026.04 | 52.1 | |
| ADAPTFUSEBase Model=Qwen 2.5 7B2026.04 | 50.4 | |
| Oracle LearningBase Model=Gemma 2 9B2026.04 | 48.6 | |
| Oracle LearningBase Model=Llama 3 8B2026.04 | 45.1 | |
| Oracle LearningBase Model=Qwen 2.5 7B2026.04 | 40.6 | |
| Self-consistencyBase Model=Gemma 2 9B, N=52026.04 | 40.4 | |
| Self-consistencyBase Model=Llama 3 8B, N=52026.04 | 38.1 | |
| Self-consistencyBase Model=Qwen 2.5 7B, N=52026.04 | 37.2 | |
| CoTBase Model=Gemma 2 9B2026.04 | 36.2 | |
| CoTBase Model=Llama 3 8B2026.04 | 35.1 | |
| CoTBase Model=Qwen 2.5 7B2026.04 | 34.5 | |
| Direct PromptingBase Model=Gemma 2 9B2026.04 | 31.3 | |
| Direct PromptingBase Model=Qwen 2.5 7B2026.04 | 31.2 | |
| Direct PromptingBase Model=Llama 3 8B2026.04 | 30.2 |