Model comparison
GPT-6 Luna vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 45.1 on the Noometry Index. GPT-6 Luna costs 5.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. GPT-6 Luna scores higher in 2 categories and Qwen3.6 Plus in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 40.1.
- The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 60.3% for Qwen3.6 Plus.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-6 Luna | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.1 | 47.3 |
| Released | 2026-09-22 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.10 | $0.50 |
| Output $ / M tokens | $0.50 | $3 |
| Results tracked | 18 | 37 |
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), Qwen3.6 Plus: 40.6 (#125)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1583 | 1461 |
| LMArena Coding | 1448 | 1467 |
| SWE-bench Verified | — | 57.9% |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| SciCode | — | 40.7% |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
GPT-6 Luna: —, Qwen3.6 Plus: —
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 31.7 (#68), Qwen3.6 Plus: 28.5 (#89)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 68.7% | 60.3% |
| LMArena Hard Prompts | 1415 | 1449 |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |
| Epoch Capabilities Index | — | 147.67 |
Math Qwen3.6 Plus leads
GPT-6 Luna: 35.6 (#140), Qwen3.6 Plus: 50.6 (#44)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1396 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
GPT-6 Luna: 40.1 (#110), Qwen3.6 Plus: 56.1 (#40)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1458 | 1456 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), Qwen3.6 Plus: —
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual Qwen3.6 Plus leads
GPT-6 Luna: 51.0 (#111), Qwen3.6 Plus: 53.5 (#66)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1390 | 1424 |
| LMArena Chinese | 1425 | 1478 |
| LMArena Russian | 1392 | 1434 |
| LMArena Spanish | 1416 | 1432 |
| LMArena French | — | 1454 |
| LMArena German | — | 1451 |
| LMArena Japanese | — | 1389 |
| LMArena Korean | — | 1381 |
Instruction Following Too close to call
GPT-6 Luna: 74.7 (#85), Qwen3.6 Plus: 75.2 (#70)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1414 | 1425 |
Long Context Qwen3.6 Plus leads
GPT-6 Luna: 43.3 (#95), Qwen3.6 Plus: 45.1 (#48)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1417 | 1440 |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
GPT-6 Luna: 58.4 (#115), Qwen3.6 Plus: 62.4 (#78)
| Benchmark | GPT-6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1392 | 1437 |
| LMArena Creative Writing | 1357 | 1405 |
| LMArena Multi-Turn | 1400 | 1438 |
Frequently asked questions
Is GPT-6 Luna better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 45.1 on the Noometry Index. GPT-6 Luna costs 5.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Luna or Qwen3.6 Plus?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is GPT-6 Luna or Qwen3.6 Plus better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 40.6 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 Qwen3.6 Plus share?
15 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Qwen3.6 Plus has 37.