Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Investment decision alignment on P1 v1 (test)
Loading...
7.25
Overall MSE
InvestAgent
6.8512
9.5431
12.235
14.9269
Jul 9, 2025
Overall MSE
Reduction
Updated 1mo ago
Evaluation Results
Method
Method
Links
Overall MSE
Reduction
InvestAgent
Backbone=Llama-3.1, Tr...
2025.07
7.25
-44.52
InvestAgent
Backbone=GPT-3.5, Trai...
2025.07
7.46
-46.84
InvestAgent
Backbone=Qwen-2, Train...
2025.07
7.46
-56.69
Llama-3.1
Training Stage=Pre-SFT
2025.07
13.07
-
GPT-3.5
Training Stage=Pre-SFT
2025.07
14.03
-
Qwen-2
Training Stage=Pre-SFT
2025.07
17.22
-
Feedback
Search any
task
Search any
task