Benchmark Almanac

Evaligo Labs

We track 2 benchmarks that Evaligo Labs made or helped make.

0 in use 0 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
SWE-Pair Agents fix two real bugs from the same Python project using one combined issue report. Hidden tests from both pull requests grade each fix. Fixing real repositories Nov 2026 90.4% Not in cards
SWE-Race Agents fix concurrency and asynchronous lifecycle bugs in Python projects. The benchmark has 95 public and 93 private tasks. Harbor distributes 94 public tasks. Fixing real repositories Oct 2026 81.9% Not in cards