Model comparison
GPT-6 Luna vs o1
GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and o1 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 36.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 78.9% for GPT-6 Luna and 14.7% for o1.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $15 / $60 for o1.
- GPT-6 Luna accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-6 Luna | o1 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 53.3 | 40.9 |
| Released | 2026-09-22 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.10 | $15 |
| Output $ / M tokens | $0.50 | $60 |
| Results tracked | 42 | 52 |
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), o1: 46.1 (#70)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| LMArena Coding | 1439 | 1367 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1581 | — |
| SciCode | 54.6% | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 1,577 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use GPT-6 Luna leads
GPT-6 Luna: 33.3 (#54), o1: 24.6 (#117)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| APEX-Agents | 44.3% | — |
| Cybench | — | 10% |
| GDP.pdf | 23% | — |
| METR Time Horizons | — | 51.1% |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), o1: 27.9 (#111)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| ARC-AGI-1 | 86.7% | 30.7% |
| Chess Puzzles | 31% | 15% |
| LMArena Hard Prompts | 1411 | 1371 |
| DTBench | 90.1% | 74.7% |
| LMCA | 44.5% | 22.3% |
| Epoch Capabilities Index | 156.28 | 141.91 |
| ARC-AGI-2 | 59.3% | — |
| SimpleBench | — | 41.7% |
| NYT Connections (extended) | 68.7% | — |
| CritPt | 19.4% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 7% | — |
| LiveBench Data Analysis | — | 65.5% |
| LiveBench | — | 75.7% |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), o1: 36.1 (#175)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 78.9% | 14.7% |
| OTIS Mock AIME 2024-2025 | 98.9% | 73.3% |
| LMArena Math | 1416 | 1388 |
| FrontierMath Tier 4 | 56.1% | — |
| ProofBench | 64% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), o1: 41.5 (#110)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| GPQA Diamond | 90.5% | 76.8% |
| SimpleQA Verified | 41.4% | 41.1% |
| LMArena Expert | 1444 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
Multimodal GPT-6 Luna leads
GPT-6 Luna: 42.4 (#30), o1: 34.2 (#93)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| LMArena Vision | 1217 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual GPT-6 Luna leads
GPT-6 Luna: 50.5 (#117), o1: 48.6 (#142)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| LMArena Non-English | 1386 | 1358 |
| LMArena Chinese | 1433 | 1394 |
| LMArena French | 1420 | 1344 |
| LMArena German | 1369 | 1337 |
| LMArena Japanese | 1369 | 1346 |
| LMArena Korean | 1360 | 1396 |
| LMArena Russian | 1394 | 1356 |
| LMArena Spanish | 1393 | 1345 |
Instruction Following Too close to call
GPT-6 Luna: 74.3 (#99), o1: 74.8 (#86)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
GPT-6 Luna: 43.0 (#111), o1: 50.3 (#9)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| LMArena Longer Query | 1409 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.3 (#119), o1: 55.6 (#144)
| Benchmark | GPT-6 Luna | o1 |
|---|---|---|
| LMArena Text | 1391 | 1366 |
| LMArena Creative Writing | 1363 | 1348 |
| LMArena Multi-Turn | 1396 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GPT-6 Luna better than o1?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.9 on the Noometry Index.
Which is cheaper, GPT-6 Luna or o1?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; o1 lists at $15 and $60.
Is GPT-6 Luna or o1 better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 46.1 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 o1 share?
27 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and o1 has 52.