Model comparison
GPT-5.6 Luna vs Qwen Plus
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 37.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Qwen Plus in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 23.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for GPT-5.6 Luna and 17.8% for Qwen Plus.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-5.6 Luna | Qwen Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 54.6 | 37.1 |
| Released | 2026-07-09 | 2024-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 33K |
| Input $ / M tokens | $0.20 | $0.40 |
| Output $ / M tokens | $1.20 | $1.20 |
| Results tracked | 52 | 20 |
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), Qwen Plus: 38.9 (#167)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| LMArena Coding | 1466 | 1328 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1519 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 34.4 (#45), Qwen Plus: —
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), Qwen Plus: 28.4 (#107)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 49.1% | 63.3% |
| LMArena Hard Prompts | 1451 | 1317 |
| DTBench | 89.1% | 81.1% |
| LMCA | 48.5% | 24% |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| Surface Evolver Bench | 61.9% | — |
| Epoch Capabilities Index | 156.39 | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Qwen Plus: 23.3 (#271)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 17.8% |
| LMArena Math | 1458 | 1326 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| ProofBench | 60% | — |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), Qwen Plus: 27.4 (#251)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| GPQA Diamond | 91.6% | 48.1% |
| LMArena Expert | 1478 | 1328 |
| SimpleQA Verified | 41% | — |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), Qwen Plus: —
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 52.8 (#78), Qwen Plus: 45.1 (#175)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1417 | 1310 |
| LMArena Chinese | 1470 | 1347 |
| LMArena Japanese | 1411 | 1251 |
| LMArena Russian | 1428 | 1323 |
| LMArena French | 1456 | — |
| LMArena German | 1454 | — |
| LMArena Korean | 1415 | — |
| LMArena Spanish | 1448 | — |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 75.6 (#57), Qwen Plus: 68.8 (#181)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1437 | 1303 |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), Qwen Plus: 40.3 (#158)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1436 | 1324 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), Qwen Plus: 52.2 (#176)
| Benchmark | GPT-5.6 Luna | Qwen Plus |
|---|---|---|
| LMArena Text | 1431 | 1326 |
| LMArena Creative Writing | 1396 | 1293 |
| LMArena Multi-Turn | 1434 | 1336 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Qwen Plus?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 37.1 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Qwen Plus?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is GPT-5.6 Luna or Qwen Plus better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 38.9 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 Qwen Plus share?
18 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Qwen Plus has 20.