Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Research on FrontierScience Research track
Loading...
53.3
Score (%)
EvoMaster
10.036
21.268
32.5
43.732
Apr 19, 2026
May 1, 2026
May 13, 2026
May 25, 2026
Jun 6, 2026
Jun 18, 2026
Jun 30, 2026
Score (%)
Relative Improvement
Updated 24d ago
Evaluation Results
Method
Method
Links
Score (%)
Relative Improvement
EvoMaster
Backend Model=GPT-5.4,...
2026.04
53.3
191
OpenClaw
Backend Model=GPT-5.4,...
2026.04
18.3
-
GPT-5-mini High
2026.06
18.3
-
Seed2.0 Lite
2026.06
18.3
-
Gemini-3-Flash High
2026.06
11.7
-
Feedback
Search any
task
Search any
task