Beer Recommendation on Participants' empirical beer ratings
4.063Mean RatingPhi-4
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Phi-4Hardware=MacBook Pro with an M2 chip and 16Gb of memory, Deployment=Local2026.03 | 4.063 | 71.8 | 33.3 | 84.4 | 100 | |
| Ministral 3BHardware=MacBook Pro with an M2 chip and 16Gb of memory, Deployment=Local2026.03 | 3.967 | 60.5 | 13.3 | 74.3 | 100 | |
| Qwen2.5 3BHardware=MacBook Pro with an M2 chip and 16Gb of memory, Deployment=Local2026.03 | 3.92 | 55.9 | 13.3 | 85.2 | 100 | |
| Qwen3 4BHardware=MacBook Pro with an M2 chip and 16Gb of memory, Deployment=Local2026.03 | 3.89 | 58.1 | 13.3 | 77.4 | 86.7 | |
| Gemma 3 4BHardware=MacBook Pro with an M2 chip and 16Gb of memory, Deployment=Local2026.03 | 3.82 | 56 | 20 | 82.7 | 100 | |
| Llama 3.2 3BHardware=MacBook Pro with an M2 chip and 16Gb of memory, Deployment=Local2026.03 | 3.807 | 49.8 | 20 | 81.4 | 100 |