Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Reasoning on PHYBENCH
Loading...
26.26
PHYBench Score
T3S
19.2816
21.0933
22.905
24.7167
Jan 15, 2026
PHYBench Score
Updated 4d ago
Evaluation Results
Method
Method
Links
PHYBench Score
T3S
Dataset=S1K-200, Teach...
2026.01
26.26
T3S
Dataset=S1K-200, Teach...
2026.01
24.36
T3S
Dataset=BOBA-200, Teac...
2026.01
23.95
T3S
Dataset=BOBA-200, Teac...
2026.01
23.76
SFT
Dataset=S1K-200, Teach...
2026.01
22.18
SFT
Dataset=BOBA-200, Teac...
2026.01
21.79
Base
Student Model=Qwen3-8B
2026.01
20.47
SFT
Dataset=S1K-200, Teach...
2026.01
20.24
SFT
Dataset=BOBA-200, Teac...
2026.01
19.55
Feedback
Search any
task
Search any
task