feat: auto-detect pre-built Docker images across all benchmarks#456

Merged

simonrosenberg merged 6 commits intomainfrom

add-skip-build-commit0-gaia

Mar 2, 2026

Commits on Feb 27, 2026

feat: auto-detect pre-built Docker images across all benchmarks

simonrosenberg
and
claude
committed

Commits on Mar 2, 2026

fix: use gpt-4o in llm_config tests to satisfy SDK context window minimum

simonrosenberg
and
claude
committed