Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Physics Problem Solving on PHYSICS (held-out)
Loading...
20.8
DBS
EXPERT
5.304
9.327
13.35
17.373
Feb 11, 2026
DBS
DVS Avg @ 32
Updated 4d ago
Evaluation Results
Method
Method
Links
DBS
DVS Avg @ 32
EXPERT
Model=Qwen3-1.7B optim...
2026.02
20.8
-
DataChef-32B
Oracle Upper Bound=tru...
2026.02
10.4
-
Gemini-3-Pro
2026.02
9.2
69.7
Kimi-K2
2026.02
9
19.7
Qwen3-Next ⊕ Kimi-K2
Reasoning backbone=Qwe...
2026.02
8.9
48.7
DataChef-32B
2026.02
8.7
61.4
SOURCEbest
2026.02
8.5
-
SOURCEavg
2026.02
6.1
-
Qwen3-32B
2026.02
5.9
11
Feedback
Search any
task
Search any
task