Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Regression on LaMP-3 time-based split (dev)
Loading...
0.211
MAE
Raw Hist.
0.20936
0.22043
0.2315
0.24257
Jun 3, 2026
MAE
RMSE
Updated 1mo ago
Evaluation Results
Method
Method
Links
MAE
RMSE
Raw Hist.
User representation=No...
2026.06
0.211
0.515
BUMP+
User representation=Se...
2026.06
0.214
0.517
Direct Reward
User representation=Ta...
2026.06
0.218
0.517
Gemini-3 Pro
User representation=Ze...
2026.06
0.222
0.521
BUMP
User representation=Se...
2026.06
0.226
0.523
Qwen3-4B (ZS)
User representation=Ze...
2026.06
0.236
0.533
Gemini-3 Flash
User representation=Ze...
2026.06
0.239
0.534
No Pers.
User representation=No...
2026.06
0.252
0.559
Feedback
Search any
task
Search any
task