Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Online Prediction on Online Flat length T = 100
Loading...
7.9
Mean Regret
DeepSeek-V3
7.8
8.475
9.15
9.825
May 11, 2026
Mean Regret
Updated 22d ago
Evaluation Results
Method
Method
Links
Mean Regret
DeepSeek-V3
Protocol=history-free...
2026.05
7.9
DeepSeek-V3
Protocol=multi-turn no...
2026.05
8.2
Qwen-3-14B
Protocol=multi-turn no...
2026.05
9.7
Qwen-3-14B
Protocol=history-free...
2026.05
10.4
Feedback
Search any
task
Search any
task
