List your company

Add-on Deals shopping assistance on SHOPPING COMPANION benchmark

66AccuracyGPT-5
8.823.6538.553.35Mar 16, 2026

Evaluation results

MethodLinks
GPT-5Category=Closed2026.036654
Qwen3-4B-LoRA + RL (Dual&Tool-wise Reward)Category=Ours2026.035543
Qwen3-4B-LoRA + RL (Dual-reward)Category=Ours2026.035038
Qwen3-4B-LoRACategory=Ours2026.034231
GPT-4oCategory=Closed2026.034126
GPT-4.1Category=Closed2026.033924
Qwen3-MaxCategory=Closed2026.033524
Qwen3-Next-80B-A3BCategory=Open2026.032918
Qwen3-30B-A3BCategory=Open2026.032113
Qwen3-4BCategory=Open2026.03116