Model comparison
GPT-6 Luna vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 45.1 on the Noometry Index. GPT-6 Luna costs 19× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. GPT-6 Luna scores higher in 1 category and Qwen3.7 Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.3 to 35.6.
- The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 85.1% for Qwen3.7 Max.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-6 Luna | Qwen3.7 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.1 | 51.4 |
| Released | 2026-09-22 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $2.50 |
| Output $ / M tokens | $0.50 | $7.50 |
| Results tracked | 18 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 54.7 (#24), Qwen3.7 Max: 50.2 (#43)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1583 | 1515 |
| LMArena Coding | 1448 | 1498 |
| SWE-bench Verified | — | 77.3% |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| SciCode | — | 48.8% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Not comparable
GPT-6 Luna: —, Qwen3.7 Max: 21.8 (#129)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
GPT-6 Luna: 31.7 (#68), Qwen3.7 Max: 48.4 (#36)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| NYT Connections (extended) | 68.7% | 85.1% |
| LMArena Hard Prompts | 1415 | 1483 |
| SimpleBench | — | 70.4% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.74 |
Math Qwen3.7 Max leads
GPT-6 Luna: 35.6 (#140), Qwen3.7 Max: 62.3 (#26)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1396 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
Knowledge Qwen3.7 Max leads
GPT-6 Luna: 40.1 (#110), Qwen3.7 Max: 61.7 (#24)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1458 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), Qwen3.7 Max: —
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual Qwen3.7 Max leads
GPT-6 Luna: 51.0 (#111), Qwen3.7 Max: 57.1 (#13)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1390 | 1475 |
| LMArena Chinese | 1425 | 1533 |
| LMArena Russian | 1392 | 1482 |
| LMArena Spanish | 1416 | — |
Instruction Following Qwen3.7 Max leads
GPT-6 Luna: 74.7 (#85), Qwen3.7 Max: 76.9 (#34)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1414 | 1460 |
Long Context Qwen3.7 Max leads
GPT-6 Luna: 43.3 (#95), Qwen3.7 Max: 45.4 (#34)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1417 | 1484 |
Writing & Preference Qwen3.7 Max leads
GPT-6 Luna: 58.4 (#115), Qwen3.7 Max: 65.2 (#52)
| Benchmark | GPT-6 Luna | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1392 | 1476 |
| LMArena Creative Writing | 1357 | 1450 |
| LMArena Multi-Turn | 1400 | 1482 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is GPT-6 Luna better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 45.1 on the Noometry Index. GPT-6 Luna costs 19× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Luna or Qwen3.7 Max?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is GPT-6 Luna or Qwen3.7 Max better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 50.2 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 1M.
How many benchmarks do GPT-6 Luna and Qwen3.7 Max share?
14 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Qwen3.7 Max has 33.