Recommendation on Amazon (Accuracy)
94.91AccuracyTALLRec
Evaluation Results
| Method | Links | |
|---|---|---|
| TALLRecInference Setting=Direct Full-history Sequence Models w/o Preference Inference2026.01 | 94.91 | |
| ALIGNXPLORE+Inference Setting=Full-history Preference Inference2026.01 | 86.39 | |
| Qwen3-32BthinkingInference Setting=Full-history Preference Inference2026.01 | 85.69 | |
| Qwen3-32BthinkingInference Setting=Streaming Preference Inference2026.01 | 85.35 | |
| ALIGNXPLORE+Inference Setting=Streaming Preference Inference2026.01 | 85.35 | |
| Qwen3-8BthinkingInference Setting=Full-history Preference Inference2026.01 | 84.68 | |
| GPT-OSS-20BInference Setting=Streaming Preference Inference2026.01 | 84.55 | |
| Qwen3-8Bnon-thinkingInference Setting=Direct Full-history Sequence Models w/o Preference Inference2026.01 | 84.05 | |
| GPT-OSS-20BInference Setting=Full-history Preference Inference2026.01 | 83.75 | |
| Qwen3-8BthinkingInference Setting=Streaming Preference Inference2026.01 | 83.58 | |
| DS-R1-Distill-Qwen-7BInference Setting=Full-history Preference Inference2026.01 | 82.82 | |
| DeepSeek-R1-671BInference Setting=Full-history Preference Inference2026.01 | 82.15 | |
| DS-R1-Distill-Qwen-7BInference Setting=Streaming Preference Inference2026.01 | 81.78 | |
| DeepSeek-R1-671BInference Setting=Streaming Preference Inference2026.01 | 80.54 | |
| ALIGNXPLOREInference Setting=Streaming Preference Inference2026.01 | 79.01 | |
| ALIGNXPLOREInference Setting=Full-history Preference Inference2026.01 | 78.58 |