Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Molecular-dynamics input-script authoring on LAMMPS 9-task transfer benchmark
Loading...
7.78
LLM-judge Mean Score
SIGA
4.4312
5.3006
6.17
7.0394
Jun 8, 2026
LLM-judge Mean Score
Gain
Updated 1mo ago
Evaluation Results
Method
Method
Links
LLM-judge Mean Score
Gain
SIGA
Backbone=deepseek-v4-f...
2026.06
7.78
3.22
SIGA
Backbone=Claude Sonnet...
2026.06
6.89
0.56
Vanilla
Backbone=Claude Sonnet...
2026.06
6.33
-
Vanilla
Backbone=deepseek-v4-f...
2026.06
4.56
-
Feedback
Search any
task
Search any
task