Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Discipline Scientific Reasoning on WildSci (test)
Loading...
58.5
Sci Score
LLMZERO
52.78
54.265
55.75
57.235
Jun 16, 2026
Sci Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Sci Score
LLMZERO
Type=Adaptive, Backbon...
2026.06
58.5
Skill-based LLM agent
Type=Adaptive, Backbon...
2026.06
56.6
Random search
Type=Static, Backbone=...
2026.06
55.8
Qwen3-4B
Type=–, Backbone=Qwen3...
2026.06
53.6
Practitioner
Type=Static, Backbone=...
2026.06
53.2
Grid search
Type=Static, Backbone=...
2026.06
53
Feedback
Search any
task
Search any
task