Model comparison
GPT-5.6 Luna vs Qwen Max
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 34.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for GPT-5.6 Luna and 16.1% for Qwen Max.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 33K.
Side by side
| GPT-5.6 Luna | Qwen Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 54.7 | 34.4 |
| Released | 2026-07-09 | 2024-04-03 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 33K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.20 | $1.60 |
| Output $ / M tokens | $1.20 | $6.40 |
| Results tracked | 51 | 23 |
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: 53.9 (#25), Qwen Max: 30.3 (#288)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| LMArena Coding | 1466 | 1288 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| Aider Polyglot | — | 21.8% |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1517 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 35.3 (#37), Qwen Max: —
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.5 (#38), Qwen Max: 24.1 (#154)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1270 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| Epoch Capabilities Index | 156.32 | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.5 (#12), Qwen Max: 21.0 (#272)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 16.1% |
| LMArena Math | 1455 | 1275 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| ProofBench | 60% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.6 (#31), Qwen Max: 30.3 (#222)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| GPQA Diamond | 91.6% | 56.1% |
| LMArena Expert | 1479 | 1248 |
| SimpleQA Verified | 41% | — |
Multimodal Not comparable
GPT-5.6 Luna: 43.0 (#22), Qwen Max: —
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| LMArena Vision | 1259 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 53.0 (#73), Qwen Max: 42.0 (#197)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| LMArena Non-English | 1418 | 1263 |
| LMArena Chinese | 1469 | 1254 |
| LMArena French | 1457 | 1329 |
| LMArena German | 1459 | 1254 |
| LMArena Japanese | 1416 | 1205 |
| LMArena Korean | 1414 | 1141 |
| LMArena Russian | 1428 | 1274 |
| LMArena Spanish | 1445 | 1290 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 76.0 (#48), Qwen Max: 66.7 (#203)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1440 | 1262 |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#78), Qwen Max: 39.4 (#175)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1437 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.3 (#27), Qwen Max: 48.0 (#200)
| Benchmark | GPT-5.6 Luna | Qwen Max |
|---|---|---|
| LMArena Text | 1432 | 1282 |
| LMArena Creative Writing | 1397 | 1248 |
| LMArena Multi-Turn | 1433 | 1277 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Qwen Max?
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 34.4 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Qwen Max?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is GPT-5.6 Luna or Qwen Max better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 33K.
How many benchmarks do GPT-5.6 Luna and Qwen Max share?
19 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Qwen Max has 23.