Model results
SWE-rebench
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
SWE-rebench
- Source
- SWE-rebench (reviewed publisher results)
- Version
- 2026-05-15_2026-07-01
- Measurement date
- Not reported
- Metric
- % · Higher is better
- Evaluation scope
- resolved-rate; 111 problems from 65 repositories; task window 2026-05-15 to 2026-07-01; model track; configuration GPT-5.6 Luna [medium]; tools interaction mode; minimal ReAct framework; mean resolved rate over five full-benchmark runs; published resolved mean 43.6% with SEM 1.47 percentage points; SEM is standard error of the mean, not a confidence interval or standard deviation; publisher context policy 128K tokens unless the model supports less; developer-recommended default generation settings; declared-model match to Atlas openai/gpt-5.6-luna-20260709; exact execution backend and API request model identifier unverified; publisher model release date 2026-06-26 is not a measurement date or proof of the Atlas dated execution; publisher flags potential contamination because its model release date follows the task-window start; this is not proof of training contamination; result date not supplied; source captured 2026-09-10
Fewer than two comparable models. No ranking is assigned. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.
GPT-5.6 Luna
openai/gpt-5.6-luna-20260709
43.6%
View modelEvidence independent