Model comparison
GPT-6 Luna vs o3-mini
GPT-6 Luna is the stronger model overall, scoring 53.3 to 36.7 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and o3-mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 28.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 78.9% for GPT-6 Luna and 18.6% for o3-mini.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- GPT-6 Luna accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-6 Luna | o3-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 53.3 | 36.7 |
| Released | 2026-09-22 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.10 | $1.10 |
| Output $ / M tokens | $0.50 | $4.40 |
| Results tracked | 42 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 55.5 (#25), o3-mini: 40.8 (#132)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| SciCode | 54.6% | 39.8% |
| LMArena Coding | 1439 | 1378 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1581 | — |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 1,577 | — |
Agentic & Tool Use GPT-6 Luna leads
GPT-6 Luna: 33.3 (#54), o3-mini: 29.6 (#84)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| APEX-Agents | 44.3% | — |
| Cybench | — | 22.5% |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), o3-mini: 16.3 (#305)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| ARC-AGI-2 | 59.3% | 3% |
| ARC-AGI-1 | 86.7% | 34.5% |
| CritPt | 19.4% | 0.3% |
| Chess Puzzles | 31% | 17% |
| LMArena Hard Prompts | 1411 | 1366 |
| Mystery Game Puzzles | 7% | 7% |
| DTBench | 90.1% | 68.8% |
| LMCA | 44.5% | 19% |
| Epoch Capabilities Index | 156.28 | 140.34 |
| SimpleBench | — | 22.8% |
| NYT Connections (extended) | 68.7% | — |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), o3-mini: 28.1 (#244)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 78.9% | 18.6% |
| FrontierMath Tier 4 | 56.1% | 0% |
| OTIS Mock AIME 2024-2025 | 98.9% | 76.9% |
| LMArena Math | 1416 | 1396 |
| ProofBench | 64% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), o3-mini: 38.3 (#146)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| GPQA Diamond | 90.5% | 77% |
| SimpleQA Verified | 41.4% | 15.3% |
| LMArena Expert | 1444 | 1364 |
| Confabulations | — | 17.9% |
Multimodal Not comparable
GPT-6 Luna: 42.4 (#30), o3-mini: —
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| LMArena Vision | 1217 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual GPT-6 Luna leads
GPT-6 Luna: 50.5 (#117), o3-mini: 45.7 (#164)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| LMArena Non-English | 1386 | 1319 |
| LMArena Chinese | 1433 | 1379 |
| LMArena French | 1420 | 1334 |
| LMArena German | 1369 | 1303 |
| LMArena Japanese | 1369 | 1286 |
| LMArena Korean | 1360 | 1314 |
| LMArena Russian | 1394 | 1304 |
| LMArena Spanish | 1393 | 1321 |
Instruction Following Too close to call
GPT-6 Luna: 74.3 (#99), o3-mini: 75.1 (#72)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1409 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context GPT-6 Luna leads
GPT-6 Luna: 43.0 (#111), o3-mini: 33.8 (#256)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| LMArena Longer Query | 1409 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.3 (#119), o3-mini: 50.3 (#182)
| Benchmark | GPT-6 Luna | o3-mini |
|---|---|---|
| LMArena Text | 1391 | 1337 |
| LMArena Creative Writing | 1363 | 1286 |
| LMArena Multi-Turn | 1396 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GPT-6 Luna better than o3-mini?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 36.7 on the Noometry Index.
Which is cheaper, GPT-6 Luna or o3-mini?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is GPT-6 Luna or o3-mini better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 200K.
How many benchmarks do GPT-6 Luna and o3-mini share?
31 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and o3-mini has 51.