Model comparison
GPT-6.1 Sol vs GPT-6 Luna
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 53.3 on the Noometry Index. GPT-6 Luna costs 20× 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-6.1 Sol scores higher in 10 categories and GPT-6 Luna in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 48.2.
- The biggest single-benchmark swing is Mystery Game Puzzles: 80% for GPT-6.1 Sol and 7% for GPT-6 Luna.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
Side by side
| GPT-6.1 Sol | GPT-6 Luna | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 65.6 | 53.3 |
| Released | 2026-09-29 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $10 | $0.50 |
| Results tracked | 34 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), GPT-6 Luna: 55.5 (#25)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| DeepSWE | 75.2% | 66.6% |
| FrontierCode | 50.2% | 42.4% |
| LMArena WebDev | 1755 | 1581 |
| SciCode | 55.8% | 54.6% |
| LMArena Coding | 1487 | 1439 |
| ALE-Bench | — | 1,577 |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), GPT-6 Luna: 33.3 (#54)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| APEX-Agents | 60% | 44.3% |
| GDP.pdf | 32% | 23% |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), GPT-6 Luna: 48.2 (#41)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| ARC-AGI-2 | 94.2% | 59.3% |
| NYT Connections (extended) | 95.5% | 68.7% |
| ARC-AGI-1 | 98.5% | 86.7% |
| CritPt | 31.7% | 19.4% |
| Chess Puzzles | 61% | 31% |
| LMArena Hard Prompts | 1466 | 1411 |
| Mystery Game Puzzles | 80% | 7% |
| Epoch Capabilities Index | 166.09 | 156.28 |
| EBR-Bench | 54.3% | — |
| DTBench | — | 90.1% |
| LMCA | — | 44.5% |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), GPT-6 Luna: 76.1 (#15)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 93.7% | 78.9% |
| FrontierMath Tier 4 | 100% | 56.1% |
| OTIS Mock AIME 2024-2025 | 100% | 98.9% |
| ProofBench | 99% | 64% |
| LMArena Math | 1464 | 1416 |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), GPT-6 Luna: 57.0 (#41)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | 95.4% | 90.5% |
| SimpleQA Verified | 73.9% | 41.4% |
| LMArena Expert | 1502 | 1444 |
Multimodal GPT-6.1 Sol leads
GPT-6.1 Sol: 52.7 (#5), GPT-6 Luna: 42.4 (#30)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| LMArena Vision | 1288 | 1217 |
| Furniture Assembly | 80% | 44.2% |
| Blueprint-Bench 2 | — | 31.2% |
Multilingual GPT-6.1 Sol leads
GPT-6.1 Sol: 54.3 (#46), GPT-6 Luna: 50.5 (#117)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1438 | 1386 |
| LMArena Chinese | 1477 | 1433 |
| LMArena Russian | 1455 | 1394 |
| LMArena French | — | 1420 |
| LMArena German | — | 1369 |
| LMArena Japanese | — | 1369 |
| LMArena Korean | — | 1360 |
| LMArena Spanish | — | 1393 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), GPT-6 Luna: 74.3 (#99)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1468 | 1409 |
Long Context GPT-6.1 Sol leads
GPT-6.1 Sol: 44.9 (#54), GPT-6 Luna: 43.0 (#111)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1465 | 1409 |
Writing & Preference GPT-6.1 Sol leads
GPT-6.1 Sol: 63.6 (#63), GPT-6 Luna: 58.3 (#119)
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1447 | 1391 |
| LMArena Creative Writing | 1432 | 1363 |
| LMArena Multi-Turn | 1449 | 1396 |
Frequently asked questions
Is GPT-6.1 Sol better than GPT-6 Luna?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 53.3 on the Noometry Index. GPT-6 Luna costs 20× 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-6.1 Sol 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-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or GPT-6 Luna better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 55.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do GPT-6.1 Sol and GPT-6 Luna share?
33 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and GPT-6 Luna has 42.