Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Classification on LaMP-2 time-based split (dev)
Loading...
89.9
Accuracy
BUMP+
55.164
64.182
73.2
82.218
Jun 3, 2026
Accuracy
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
BUMP+
User representation=Se...
2026.06
89.9
84.7
BUMP
User representation=Se...
2026.06
89.4
84.5
Direct Reward
User representation=Ta...
2026.06
88.9
84
Raw Hist.
User representation=No...
2026.06
88.8
81.3
Gemini-3 Pro
User representation=Ze...
2026.06
88
83.4
Gemini-3 Flash
User representation=Ze...
2026.06
77.9
70.3
Qwen3-4B (ZS)
User representation=Ze...
2026.06
71.3
65.5
No Pers.
User representation=No...
2026.06
56.5
52.8
Feedback
Search any
task
Search any
task