Model comparison
GPT-5.6 Luna vs o3-mini
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 36.7 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GPT-5.6 Luna scores higher in 9 categories and o3-mini in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 28.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 82.1% for GPT-5.6 Luna and 18.6% for o3-mini.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-5.6 Luna | o3-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 54.6 | 36.7 |
| Released | 2026-07-09 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.20 | $1.10 |
| Output $ / M tokens | $1.20 | $4.40 |
| Results tracked | 52 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 54.5 (#28), o3-mini: 40.8 (#132)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| SciCode | 53.6% | 39.8% |
| WeirdML | 60.9% | 43.7% |
| LMArena Coding | 1466 | 1378 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| Aider Polyglot | — | 60.4% |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1519 | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use GPT-5.6 Luna leads
GPT-5.6 Luna: 34.4 (#45), o3-mini: 29.6 (#84)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| APEX-Agents | 43% | — |
| Cybench | — | 22.5% |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), o3-mini: 16.3 (#305)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| ARC-AGI-2 | 59.5% | 3% |
| SimpleBench | 46.8% | 22.8% |
| ARC-AGI-1 | 88% | 34.5% |
| CritPt | 20.6% | 0.3% |
| Chess Puzzles | 40% | 17% |
| LMArena Hard Prompts | 1451 | 1366 |
| Mystery Game Puzzles | 21% | 7% |
| DTBench | 89.1% | 68.8% |
| LMCA | 48.5% | 19% |
| Epoch Capabilities Index | 156.39 | 140.34 |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| Surface Evolver Bench | 61.9% | — |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), o3-mini: 28.1 (#244)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.1% | 18.6% |
| FrontierMath Tier 4 | 61% | 0% |
| OTIS Mock AIME 2024-2025 | 98.3% | 76.9% |
| LMArena Math | 1458 | 1396 |
| ProofBench | 60% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), o3-mini: 38.3 (#146)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| GPQA Diamond | 91.6% | 77% |
| SimpleQA Verified | 41% | 15.3% |
| LMArena Expert | 1478 | 1364 |
| Confabulations | — | 17.9% |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), o3-mini: —
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 52.8 (#78), o3-mini: 45.7 (#164)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| LMArena Non-English | 1417 | 1319 |
| LMArena Chinese | 1470 | 1379 |
| LMArena French | 1456 | 1334 |
| LMArena German | 1454 | 1303 |
| LMArena Japanese | 1411 | 1286 |
| LMArena Korean | 1415 | 1314 |
| LMArena Russian | 1428 | 1304 |
| LMArena Spanish | 1448 | 1321 |
Instruction Following Too close to call
GPT-5.6 Luna: 75.6 (#57), o3-mini: 75.1 (#72)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1437 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), o3-mini: 33.8 (#256)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| LMArena Longer Query | 1436 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), o3-mini: 50.3 (#182)
| Benchmark | GPT-5.6 Luna | o3-mini |
|---|---|---|
| LMArena Text | 1431 | 1337 |
| LMArena Creative Writing | 1396 | 1286 |
| LMArena Multi-Turn | 1434 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GPT-5.6 Luna better than o3-mini?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 36.7 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or o3-mini?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is GPT-5.6 Luna or o3-mini better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 200K.
How many benchmarks do GPT-5.6 Luna and o3-mini share?
33 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and o3-mini has 51.