Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Judgmental event forecasting on Polymarket (val)
Loading...
0.305
NCE Loss
Qwen 3B
0.25076
0.61688
0.983
1.34912
Jun 14, 2026
NCE Loss
Updated 1mo ago
Evaluation Results
Method
Method
Links
NCE Loss
Qwen 3B
Training stage=End, Po...
2026.06
0.305
Qwen 7B
Training stage=End, Po...
2026.06
0.406
Qwen 1.5B
Training stage=End, Po...
2026.06
0.415
Claude 3.5 Sonnet
Reference model compar...
2026.06
0.62
Qwen 3B
Training stage=Start,...
2026.06
0.975
Qwen 7B
Training stage=Start,...
2026.06
0.995
Qwen 1.5B
Training stage=Start,...
2026.06
1.661
Feedback
Search any
task
Search any
task