Model comparison
GPT-5.6 Luna vs Qwen3.6 Plus
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 47.5 on the Noometry Index.
Last verified . 32 shared benchmarks.
Alibaba (Qwen)Summary
- They share 32 benchmarks with published results for both. GPT-5.6 Luna scores higher in 6 categories and Qwen3.6 Plus in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 51.8.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 82.1% for GPT-5.6 Luna and 38.2% for Qwen3.6 Plus.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-5.6 Luna | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 54.6 | 47.5 |
| Released | 2026-07-09 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.20 | $0.50 |
| Output $ / M tokens | $1.20 | $3 |
| Results tracked | 52 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 54.5 (#28), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1519 | 1461 |
| SciCode | 53.6% | 40.7% |
| LMArena Coding | 1466 | 1467 |
| ALE-Bench | 1,667 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| WeirdML | 60.9% | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 34.4 (#45), Qwen3.6 Plus: —
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 4,095 | 5,115 |
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 69.4% | 60.3% |
| CritPt | 20.6% | 2.9% |
| Chess Puzzles | 40% | 17% |
| LMArena Hard Prompts | 1451 | 1449 |
| Mystery Game Puzzles | 21% | 12% |
| DTBench | 89.1% | 81.9% |
| LMCA | 48.5% | 33.1% |
| Epoch Capabilities Index | 156.39 | 147.65 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| ARC-AGI-1 | 88% | — |
| Thematic Generalization | — | 59.5% |
| Surface Evolver Bench | 61.9% | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.1% | 38.2% |
| OTIS Mock AIME 2024-2025 | 98.3% | 93.3% |
| LMArena Math | 1458 | 1450 |
| FrontierMath Tier 4 | 61% | — |
| ProofBench | 60% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 91.6% | 88.4% |
| SimpleQA Verified | 41% | 44.1% |
| LMArena Expert | 1478 | 1454 |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), Qwen3.6 Plus: —
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual Too close to call
GPT-5.6 Luna: 52.8 (#78), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1417 | 1424 |
| LMArena Chinese | 1470 | 1477 |
| LMArena French | 1456 | 1455 |
| LMArena German | 1454 | 1452 |
| LMArena Japanese | 1411 | 1389 |
| LMArena Korean | 1415 | 1379 |
| LMArena Russian | 1428 | 1434 |
| LMArena Spanish | 1448 | 1432 |
Instruction Following Too close to call
GPT-5.6 Luna: 75.6 (#57), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1437 | 1425 |
Long Context Qwen3.6 Plus leads
GPT-5.6 Luna: 43.9 (#82), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1436 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | GPT-5.6 Luna | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1431 | 1437 |
| LMArena Creative Writing | 1396 | 1404 |
| LMArena Multi-Turn | 1434 | 1438 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Qwen3.6 Plus?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 47.5 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Qwen3.6 Plus?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is GPT-5.6 Luna or Qwen3.6 Plus better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 1M.
How many benchmarks do GPT-5.6 Luna and Qwen3.6 Plus share?
32 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Qwen3.6 Plus has 37.