Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Virtual Screening on Tox21 NR-AR-LBD 3.5% prevalence
Loading...
0.401
DQS
DeepSeek-V3.1
-0.01188
0.09531
0.2025
0.30969
Mar 12, 2026
DQS
Updated 1mo ago
Evaluation Results
Method
Method
Links
DQS
DeepSeek-V3.1
Mode=Direct
2026.03
0.401
DeepSeek-V3.1
Mode=FewDirect
2026.03
0.383
Llama-4-Maverick
Mode=Direct
2026.03
0.363
GLM-5
Mode=FewDirect
2026.03
0.357
GLM-5
Mode=Direct
2026.03
0.351
Llama-4-Maverick
Mode=FewDirect
2026.03
0.222
GLM-5
Mode=Rerank
2026.03
0.141
GLM-5
Mode=FewRerank
2026.03
0.097
Greedy-ML
2026.03
0.086
DeepSeek-V3.1
Mode=Rerank
2026.03
0.071
DeepSeek-V3.1
Mode=FewRerank
2026.03
0.065
Llama-4-Maverick
Mode=Rerank
2026.03
0.042
Llama-4-Maverick
Mode=FewRerank
2026.03
0.004
Feedback
Search any
task
Search any
task