Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Ideation on Scientific Ideation Out-of-Domain
Loading...
59
GPT-5.2 Score
SciThinker-30B
35.08
41.29
47.5
53.71
Mar 15, 2026
GPT-5.2 Score
GLM-5 Score
Gemini 3 Pro Score
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
GPT-5.2 Score
GLM-5 Score
Gemini 3 Pro Score
Average Score
SciThinker-30B
Base Policy=Qwen3-30B-...
2026.03
59
61
42.5
54.2
Qwen3-30B
Base Policy=Qwen3-30B-...
2026.03
36
29.5
18
27.8
Feedback
Search any
task
Search any
task