Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Formal theorem proving on PhysLeanData (test)
Loading...
58.8
Classical Score
PhysProver
34.36
40.705
47.05
53.395
Jan 22, 2026
Classical Score
Particle & String Score
Relativity Score
QFT Score
Overall Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Classical Score
Particle & String Score
Relativity Score
QFT Score
Overall Score
PhysProver
Backbone=DeepSeek-Prov...
2026.01
58.8
26.9
39.3
26.8
36.4
Deepseek-Prover-V2-7B
Model Type=Open-source...
2026.01
54.9
23.9
37.7
25.4
34
Claude-4.5-Sonnet
Model Type=Proprietary...
2026.01
52.9
19.4
29.5
39.4
34.4
Goedel-Prover-V2-8B
Model Type=Open-source...
2026.01
49
19.4
34.4
28.2
31.6
GPT-5
Model Type=Proprietary...
2026.01
37.3
13.4
21.3
35.2
26.4
Kimina-Prover-Distill-8B
Model Type=Open-source...
2026.01
35.3
14.9
29.5
22.5
24.8
Feedback
Search any
task
Search any
task