GPT-5.6 Luna Non-reasoning
| Released | 2026-07-09 |
|---|---|
| Price per 1M | $0.20 in · $1.20 out |
| Overall score | 46.3 · rank 317 |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Non-reasoning |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 46.3 | 317 | 9 |
| Overall: Coding | 45.8 | 321 | 7 |
| Overall: Reasoning | 46.5 | 309 | 8 |
| Overall: Agentic work | 44.8 | 332 | 7 |
| Overall: Frontend | 46.6 | 265 | 1 |
| Coding | 46.6 | 284 | 1 |
| Reasoning | 41.7 | 352 | 6 |
| Math | 52.6 | 152 | 2 |
| Value vs price | −1.7 | 266 |
Evidence
Coding 46.6 ±4.7
Reasoning 41.7 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 (ARC Prize verified) | 0.8% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 3.3% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 63.6% | Epoch AI | 2026-08-07 |
| CritPt | 0.3% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 3.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 20.0% | Epoch AI | 2026-08-30 |
Math 52.6 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 39.7% | Epoch AI | 2026-08-29 |
| OTIS Mock AIME 2024-2025 | 40.0% | Epoch AI | 2026-08-07 |
Names matched to this model
gpt-5-6-luna-non-reasoning