GPT-5.6 Luna Medium
| Released | 2026-07-09 |
|---|---|
| Price per 1M | $0.20 in · $1.20 out |
| Overall score | 52.1 (early, few results) |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Medium |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 52.1 | 9 | |
| Overall: Coding | 52.0 | 9 | |
| Overall: Reasoning | 52.3 | 5 | |
| Overall: Agentic work | 52.1 | 9 | |
| Overall: Frontend | 51.9 | 4 | |
| Coding | 51.9 | 4 | |
| Reasoning | 52.3 | 5 | |
| Value vs price | +4.0 |
Evidence
Coding 51.9 ±1.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 22.2% | Epoch AI | 2026-11-11 |
| DeepSWE | 11.3% | Epoch AI | 2026-11-11 |
| SWE-rebench | 43.6% | SWE-rebench | 2026-07-01 |
| SciCode | 46.8% | Epoch AI | 2026-11-11 |
Reasoning 52.3 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 7.4% | Epoch AI | 2026-11-11 |
| CritPt | 4.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 56.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 7.4% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 56.5% | Epoch AI | 2026-11-11 |
| ARC-AGI-3 | 0.2% | ARC Prize | 2026-11-11 |
| Mystery Game Puzzles | 12.0% | Epoch AI | 2026-08-27 |
Names matched to this model
gpt-5-6-luna-medium