Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
STEM Knowledge on BABE
Loading...
58.1
Score
GPT-5.2 High
39.692
44.471
49.25
54.029
Jun 30, 2026
Score
Updated 24d ago
Evaluation Results
Method
Method
Links
Score
GPT-5.2 High
2026.06
58.1
Gemini-3-Flash
Tier=High
2026.06
55.2
Gemini-3-pro High
2026.06
51.3
Seed2.0 Lite
2026.06
50.2
Seed2.0 Pro
2026.06
50
Claude-Opus-4.5
2026.06
49.3
GPT-5-mini
Tier=High
2026.06
49.2
Claude-Sonnet-4.5
2026.06
44.7
Seed2.0 Mini
2026.06
40.4
Feedback
Search any
task
Search any
task