Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
STEM on PhyX openended
Loading...
72.1
Pass@1
Seed2.0 Pro
60.868
63.784
66.7
69.616
Jun 30, 2026
Pass@1
Updated 23d ago
Evaluation Results
Method
Method
Links
Pass@1
Seed2.0 Pro
2026.06
72.1
GPT-5.2 High
2026.06
71.5
Gemini-3-Pro High
2026.06
71
Seed1.8
2026.06
65.9
Seed2.0 Mini
2026.06
65
Seed2.0 Lite
2026.06
62.8
Claude-Opus-4.5
2026.06
61.3
Feedback
Search any
task
Search any
task