Model comparison
GPT-5.5 Pro vs GPT-6 Luna
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 53.3 on the Noometry Index. GPT-6 Luna costs 338× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GPT-5.5 Pro scores higher in 3 categories and GPT-6 Luna in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.5 Pro leads 73.3 to 48.2.
- The biggest single-benchmark swing is Chess Puzzles: 64% for GPT-5.5 Pro and 31% for GPT-6 Luna.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $30 / $180 for GPT-5.5 Pro.
Side by side
| GPT-5.5 Pro | GPT-6 Luna | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 64.3 | 53.3 |
| Released | 2026-04-23 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $30 | $0.10 |
| Output $ / M tokens | $180 | $0.50 |
| Results tracked | 14 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.5 Pro: —, GPT-6 Luna: 55.5 (#25)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| LMArena WebDev | — | 1581 |
| SciCode | — | 54.6% |
| LMArena Coding | — | 1439 |
| ALE-Bench | — | 1,577 |
Agentic & Tool Use Not comparable
GPT-5.5 Pro: —, GPT-6 Luna: 33.3 (#54)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| APEX-Agents | — | 44.3% |
| GDP.pdf | — | 23% |
Reasoning GPT-5.5 Pro leads
GPT-5.5 Pro: 73.3 (#10), GPT-6 Luna: 48.2 (#41)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| ARC-AGI-2 | 84.6% | 59.3% |
| ARC-AGI-1 | 96.5% | 86.7% |
| CritPt | 30.6% | 19.4% |
| Chess Puzzles | 64% | 31% |
| DTBench | 96% | 90.1% |
| LMCA | 53.9% | 44.5% |
| Epoch Capabilities Index | 162.07 | 156.28 |
| SimpleBench | 76.9% | — |
| NYT Connections (extended) | — | 68.7% |
| LMArena Hard Prompts | — | 1411 |
| Mystery Game Puzzles | — | 7% |
Math GPT-5.5 Pro leads
GPT-5.5 Pro: 84.0 (#10), GPT-6 Luna: 76.1 (#15)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87.7% | 78.9% |
| FrontierMath Tier 4 | 78% | 56.1% |
| OTIS Mock AIME 2024-2025 | 100% | 98.9% |
| ProofBench | — | 64% |
| LMArena Math | — | 1416 |
| FrontierMath (Feb 2025 set) | 52.4% | — |
| FrontierMath Tier 4 (v1) | 39.6% | — |
Knowledge GPT-5.5 Pro leads
GPT-5.5 Pro: 64.1 (#19), GPT-6 Luna: 57.0 (#41)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | 93.9% | 90.5% |
| SimpleQA Verified | — | 41.4% |
| LMArena Expert | — | 1444 |
Multimodal Not comparable
GPT-5.5 Pro: —, GPT-6 Luna: 42.4 (#30)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| LMArena Vision | — | 1217 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 44.2% |
Multilingual Not comparable
GPT-5.5 Pro: —, GPT-6 Luna: 50.5 (#117)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | — | 1386 |
| LMArena Chinese | — | 1433 |
| LMArena French | — | 1420 |
| LMArena German | — | 1369 |
| LMArena Japanese | — | 1369 |
| LMArena Korean | — | 1360 |
| LMArena Russian | — | 1394 |
| LMArena Spanish | — | 1393 |
Instruction Following Not comparable
GPT-5.5 Pro: —, GPT-6 Luna: 74.3 (#99)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | — | 1409 |
Long Context Not comparable
GPT-5.5 Pro: —, GPT-6 Luna: 43.0 (#111)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | — | 1409 |
Writing & Preference Not comparable
GPT-5.5 Pro: —, GPT-6 Luna: 58.3 (#119)
| Benchmark | GPT-5.5 Pro | GPT-6 Luna |
|---|---|---|
| LMArena Text | — | 1391 |
| LMArena Creative Writing | — | 1363 |
| LMArena Multi-Turn | — | 1396 |
Frequently asked questions
Is GPT-5.5 Pro better than GPT-6 Luna?
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 53.3 on the Noometry Index. GPT-6 Luna costs 338× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.5 Pro or GPT-6 Luna?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GPT-5.5 Pro lists at $30 and $180.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do GPT-5.5 Pro and GPT-6 Luna share?
11 benchmarks have published results for both models. GPT-5.5 Pro has 14 scored results on Noometry and GPT-6 Luna has 42.