GPT-5.6 Luna Max
| Released | 2026-07-09 |
|---|---|
| Price per 1M | $0.20 in · $1.20 out |
| Overall score | 58.6 · rank 138 |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Max |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 58.6 | 138 | 34 |
| Overall: Coding | 58.8 | 126 | 26 |
| Overall: Reasoning | 59.3 | 126 | 16 |
| Overall: Agentic work | 58.6 | 143 | 25 |
| Overall: Frontend | 58.3 | 110 | 10 |
| Coding | 59.1 | 109 | 8 |
| Agents | 58.1 | 111 | 8 |
| Reasoning | 59.7 | 135 | 9 |
| Math | 61.4 | 37 | 4 |
| Knowledge | 54.7 | 83 | 3 |
| Frontend | 58.1 | 62 | 1 |
| Multimodal | 57.2 | 58 | 1 |
| Value vs price | +10.6 | 43 |
Evidence
Coding 59.1 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 35.9% | Epoch AI | 2026-11-11 |
| DeepSWE | 67.2% | Epoch AI | 2026-11-11 |
| FrontierCode | 39.8% | Epoch AI | 2026-11-11 |
| MirrorCode | 21.1% | Epoch AI | 2026-10-21 |
| IOI | 61.8% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 93.0% | Vals AI | 2026-09-01 |
| SciCode | 53.6% | Epoch AI | 2026-11-11 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 58.1 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SRE Bench | 1.5% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 0.0% | Vals AI | 2026-11-09 |
| Terminal-Bench 4 | 17.6% | Terminal-Bench | 2026-06-26 |
| Terminal-Bench 4.0 (Vals run) | 11.6% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 79.0% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 24.8% | Vals AI | 2026-11-09 |
| SkillsBench | 60.4% | Vals AI | 2026-10-29 |
| BALROG | 45.6% | Epoch AI | 2026-11-11 |
| CyberBench v1.1 | 73.6% | Vals AI | 2026-11-05 |
Reasoning 59.7 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 59.5% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 59.6% | ARC Prize | 2026-11-11 |
| MysteryMechanism | 14.4% | Vals AI | 2026-11-09 |
| CritPt | 20.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 90.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 88.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 91.6% | Epoch AI | 2026-07-09 |
| GPQA Diamond (Vals run) | 91.7% | Vals AI | 2026-09-01 |
| BioMysteryBench | 61.5% | Vals AI | 2026-11-09 |
| ARC-AGI-3 | 0.2% | ARC Prize | 2026-11-11 |
| Chess Puzzles | 43.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 21.0% | Epoch AI | 2026-07-28 |
Math 61.4 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 82.1% | Epoch AI | 2026-07-09 |
| FrontierMath Tier 4 | 61.0% | Epoch AI | 2026-07-09 |
| OTIS Mock AIME 2024-2025 | 98.3% | Epoch AI | 2026-07-09 |
| ProofBench v1.1 | 60.0% | Vals AI | 2026-11-09 |
| ProofBench | 60.0% | Epoch AI | 2026-11-11 |
Knowledge 54.7 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 41.0% | Epoch AI | 2026-08-10 |
| MMLU-Pro (Vals run) | 86.0% | Vals AI | 2026-09-01 |
| Legal Research Bench | 36.5% | Vals AI | 2026-11-09 |
Frontend 58.1 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 77.1% | Vals AI | 2026-11-09 |
Multimodal 57.2 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 85.0% | Vals AI | 2026-09-01 |
Names matched to this model
gpt-5-6-luna-max