Recommendation on MovieLens (ML) (test)
54.17CTRDeepFM
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DeepFMEvaluation Framework=A/B Agent, Backbone=Gemini-2.5-flash2026.01 | 54.17 | 43.33 | 4.57 | — | — | |
| AFNEvaluation Framework=A/B Agent, Backbone=Gemini-2.5-flash2026.01 | 53.13 | 42.25 | 4.52 | — | — | |
| FMEvaluation Framework=A/B Agent, Backbone=Gemini-2.5-flash2026.01 | 50 | 38.55 | 4.43 | — | — | |
| PopEvaluation Framework=A/B Agent, Backbone=Gemini-2.5-flash2026.01 | 45.2 | 29.2 | 4.12 | — | — | |
| DeepFMEvaluation Framework=A/B Agent, Backbone=GPT-4o2026.01 | 44.53 | 34.58 | 4.75 | — | — | |
| AFNEvaluation Framework=A/B Agent, Backbone=GPT-4o2026.01 | 43.01 | 33.85 | 4.72 | — | — | |
| FMEvaluation Framework=A/B Agent, Backbone=GPT-4o2026.01 | 36.35 | 29.4 | 4.7 | — | — | |
| PopEvaluation Framework=A/B Agent, Backbone=GPT-4o2026.01 | 30.77 | 18.35 | 4.3 | — | — | |
| RandomEvaluation Framework=A/B Agent, Backbone=Gemini-2.5-flash2026.01 | 29.05 | 18.63 | 4.01 | — | — | |
| DeepFMEvaluation Framework=A/B Agent, Backbone=GPT-4o-mini2026.01 | 28.91 | 20.94 | 4.52 | — | — | |
| AFNEvaluation Framework=A/B Agent, Backbone=GPT-4o-mini2026.01 | 28.45 | 19.95 | 4.52 | — | — | |
| FMEvaluation Framework=A/B Agent, Backbone=GPT-4o-mini2026.01 | 26.42 | 19.84 | 4.52 | — | — | |
| RandomEvaluation Framework=A/B Agent, Backbone=GPT-4o2026.01 | 23.3 | 11.47 | 4.27 | — | — | |
| PopEvaluation Framework=A/B Agent, Backbone=GPT-4o-mini2026.01 | 18.86 | 11.81 | 4.2 | — | — | |
| RandomEvaluation Framework=A/B Agent, Backbone=GPT-4o-mini2026.01 | 8.72 | 4.61 | 4.01 | — | — | |
| AFNEvaluation Framework=Real-World2026.01 | — | — | — | 4.22 | 12.38 | |
| DeepFMEvaluation Framework=Real-World2026.01 | — | — | — | 4.29 | 11.3 | |
| FMEvaluation Framework=Real-World2026.01 | — | — | — | 3.53 | 9.87 | |
| PopEvaluation Framework=Real-World2026.01 | — | — | — | 2.16 | 8.81 | |
| RandomEvaluation Framework=Real-World2026.01 | — | — | — | 0.66 | 2.22 |