Model comparison
GPT-5.6 Luna vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 8.9× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GPT-5.6 Luna scores higher in 1 category and GPT-6.1 Sol in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 47.6.
- The biggest single-benchmark swing is Mystery Game Puzzles: 21% for GPT-5.6 Luna and 80% for GPT-6.1 Sol.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
Side by side
| GPT-5.6 Luna | GPT-6.1 Sol | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 54.6 | 65.6 |
| Released | 2026-07-09 | 2026-09-29 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.20 | $2 |
| Output $ / M tokens | $1.20 | $10 |
| Results tracked | 52 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-5.6 Luna: 54.5 (#28), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| DeepSWE | 67.2% | 75.2% |
| FrontierCode | 39.8% | 50.2% |
| LMArena WebDev | 1519 | 1755 |
| SciCode | 53.6% | 55.8% |
| LMArena Coding | 1466 | 1487 |
| CursorBench | 35.9% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-5.6 Luna: 34.4 (#45), GPT-6.1 Sol: 39.6 (#26)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | 43% | 60% |
| GDP.pdf | 22.7% | 32% |
| BALROG | 45.6% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-6.1 Sol leads
GPT-5.6 Luna: 47.6 (#43), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| ARC-AGI-2 | 59.5% | 94.2% |
| NYT Connections (extended) | 69.4% | 95.5% |
| ARC-AGI-1 | 88% | 98.5% |
| CritPt | 20.6% | 31.7% |
| Chess Puzzles | 40% | 61% |
| LMArena Hard Prompts | 1451 | 1466 |
| Mystery Game Puzzles | 21% | 80% |
| Epoch Capabilities Index | 156.39 | 166.09 |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| EBR-Bench | — | 54.3% |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
Math GPT-6.1 Sol leads
GPT-5.6 Luna: 77.7 (#14), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.1% | 93.7% |
| FrontierMath Tier 4 | 61% | 100% |
| OTIS Mock AIME 2024-2025 | 98.3% | 100% |
| ProofBench | 60% | 99% |
| LMArena Math | 1458 | 1464 |
Knowledge GPT-6.1 Sol leads
GPT-5.6 Luna: 58.5 (#34), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 91.6% | 95.4% |
| SimpleQA Verified | 41% | 73.9% |
| LMArena Expert | 1478 | 1502 |
Multimodal GPT-6.1 Sol leads
GPT-5.6 Luna: 42.7 (#28), GPT-6.1 Sol: 52.7 (#5)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | 1258 | 1288 |
| Furniture Assembly | 42.5% | 80% |
| Blueprint-Bench 2 | 22.6% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-6.1 Sol leads
GPT-5.6 Luna: 52.8 (#78), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1417 | 1438 |
| LMArena Chinese | 1470 | 1477 |
| LMArena Russian | 1428 | 1455 |
| LMArena French | 1456 | — |
| LMArena German | 1454 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1415 | — |
| LMArena Spanish | 1448 | — |
Instruction Following GPT-6.1 Sol leads
GPT-5.6 Luna: 75.6 (#57), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1437 | 1468 |
Long Context Too close to call
GPT-5.6 Luna: 43.9 (#82), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1436 | 1465 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | GPT-5.6 Luna | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1431 | 1447 |
| LMArena Creative Writing | 1396 | 1432 |
| LMArena Multi-Turn | 1434 | 1449 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 8.9× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Luna or GPT-6.1 Sol?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GPT-5.6 Luna or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 54.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do GPT-5.6 Luna and GPT-6.1 Sol share?
33 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and GPT-6.1 Sol has 34.