Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Synthetic Time Series Reasoning on TimeSeriesExam
Loading...
47.27
Accuracy
VeriTime
35.1956
38.3303
41.465
44.5997
Feb 8, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
VeriTime
Backbone=Qwen3-4B-Inst...
2026.02
47.27
VeriTime
Backbone=Qwen2.5-3B-In...
2026.02
41.67
Qwen3-4B-Instruct
Setting=Base
2026.02
37.98
Qwen2.5-3B-Instruct
Setting=Base
2026.02
35.66
Feedback
Search any
task
Search any
task