Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Inbox Sorting on PMR-Real (test)
Loading...
77
T-NDCG@10
Qwen8B_SFT
40.6
50.05
59.5
68.95
Jan 19, 2026
T-NDCG@10
T-NDCG@30
Updated 4d ago
Evaluation Results
Method
Method
Links
T-NDCG@10
T-NDCG@30
Qwen8B_SFT
Evaluation Protocol=Ur...
2026.01
77
39
MedGem27B_SFT
Evaluation Protocol=Ur...
2026.01
75
39
Reward-8B_Urgent
Evaluation Protocol=Ur...
2026.01
71
38
MedGem27B
Evaluation Protocol=0-...
2026.01
70
31
MedGem27B_SFT
Evaluation Protocol=Mu...
2026.01
66
35
Reward-4B_Urgent
Evaluation Protocol=Ur...
2026.01
65
37
MedGem27B
Evaluation Protocol=Mu...
2026.01
64
32
Qwen32B
Evaluation Protocol=Mu...
2026.01
62
34
GPT-OSS*
Evaluation Protocol=0-...
2026.01
59
32
Reward-8B_Base
Evaluation Protocol=Ur...
2026.01
54
20
Qwen8B
Evaluation Protocol=0-...
2026.01
52
18
GPT-OSS
Evaluation Protocol=Mu...
2026.01
48
23
Reward-4B_Base
Evaluation Protocol=Ur...
2026.01
48
18
Qwen32B
Evaluation Protocol=0-...
2026.01
42
17
Feedback
Search any
task
Search any
task