SWE-ABS Benchmark Results
Performance comparison of top 30 agent systems on SWE-Bench vs SWE-ABS
Total Models
0
Avg. Original
0
%
Avg. SWE-ABS
0
%
Avg. Drop
0
%
Max Drop
0
%
Min Drop
0
%
All
Rank Up
Rank Down
Big Drop (>18%)
Date
Model
Orig. (%)
SWE-ABS (%)
Drop (%)
Old Rank
New Rank
Rank Change
No results found. Try a different search term or filter.
Performance Drop Comparison