Benchmark

SWE Atlas

Reports three splits (Codebase Q&A, Test Writing, Refactoring) as separate figures; the split is part of the instrument.

Released
2026-05-08
Categories
coding_agent
Openness
unknown
Source
model_reports
Reported scores
3

Reported scores

model_reports

ModelOrganizationReported valueReportedEvidence
Hy4 previewTencent64.02026-08-28evidence
Hy4 previewTencent53.32026-08-28evidence
Hy4 previewTencent57.82026-08-28evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.