List your company

Medical Search Relevance Assessment on LocalQSMed HARD v1.0

0.6611AccuracyQwen3-32B
0.0462520.2058760.36550.525124Dec 3, 2025

Evaluation results

MethodLinks
Qwen3-32BLoss Rate=0.00%2025.120.6611
Qwen3-14BLoss Rate=0.02%2025.120.6106
DeepSeek-R1-Distill-Qwen-14BLoss Rate=0.00%2025.120.5758
Qwen3-8BLoss Rate=0.00%2025.120.549
Qwen3-4BLoss Rate=0.00%2025.120.5294
Llama-3.3-70B-InstructLoss Rate=46.86%2025.120.3737
DeepSeek-R1-Distill-Llama-70BLoss Rate=43.68%2025.120.3598
Llama-3.1-8BLoss Rate=63.55%2025.120.3504
Llama-3.2-3BLoss Rate=0.00%2025.120.3358
Llama-3.2-1BLoss Rate=63.67%2025.120.2913
Qwen3-0.6BLoss Rate=6.40%2025.120.2784
DeepSeek-R1-Distill-Qwen-7BLoss Rate=17.59%2025.120.0699