OpenAIGPT
GPT-5.6 Luna
OpenAI · GPT. Released Jul 9, 2026.
GPT-5.6 Luna is a model from OpenAI in the GPT family, released Jul 9, 2026. evals.report tracks 7 reported GPT-5.6 Luna benchmark scores across Terminal-Bench 2.1, SWE-bench Pro, GPQA Diamond, BrowseComp, MMMU-Pro, OpenAI-MRCR v2 (Multi-Round Coreference Resolution), ARC-AGI-3 — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
7 results
Benchmark results 7
Compare this model| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Agents | 84.7% | task success | Verified | Jul 9, 2026 | Details |
| SWE-bench Pro | Coding | 62.7% | % resolved | Verified | Jul 9, 2026 | Details |
| GPQA Diamond | Reasoning | 92.3% | accuracy | Verified | Jul 9, 2026 | Details |
| BrowseComp | Agents | 83.3% | accuracy | Verified | Jul 9, 2026 | Details |
| MMMU-Pro | Multimodal | 78.4% | accuracy | Verified | Jul 9, 2026 | Details |
| OpenAI-MRCR v2 (Multi-Round Coreference Resolution) | Reasoning | 41.3% | accuracy (mean SequenceMatcher similarity) | Verified | Jul 9, 2026 | Details |
| ARC-AGI-3 | Reasoning | 0.18% | accuracy | Verified | Jul 9, 2026 | Details |