Model comparison
GPT-5.6 Luna vs Qwen2.5-Coder-32B
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 32.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Qwen2.5-Coder-32B 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 30.8.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 54.7 | 32.9 |
| Released | 2026-07-09 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 33K |
| Max output | 128K | 29K |
| Input $ / M tokens | $0.20 | $0.66 |
| Output $ / M tokens | $1.20 | $1 |
| Results tracked | 51 | 31 |
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), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1466 | 1276 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1517 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 1,667 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 35.3 (#37), Qwen2.5-Coder-32B: —
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| 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), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1251 |
| Epoch Capabilities Index | 156.32 | 119.41 |
| 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% | — |
| LiveBench Reasoning | — | 42.1% |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.5 (#12), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1455 | 1251 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.6 (#31), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1479 | 1221 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
GPT-5.6 Luna: 43.0 (#22), Qwen2.5-Coder-32B: —
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| 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), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1418 | 1205 |
| LMArena Chinese | 1469 | 1222 |
| LMArena Russian | 1428 | 1228 |
| LMArena French | 1457 | — |
| LMArena German | 1459 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1414 | — |
| LMArena Spanish | 1445 | — |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 76.0 (#48), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1440 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#78), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1437 | 1251 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.3 (#27), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | GPT-5.6 Luna | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1432 | 1230 |
| LMArena Creative Writing | 1397 | 1174 |
| LMArena Multi-Turn | 1433 | 1222 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is GPT-5.6 Luna better than Qwen2.5-Coder-32B?
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 32.9 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Qwen2.5-Coder-32B?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is GPT-5.6 Luna or Qwen2.5-Coder-32B better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 22.4 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 Qwen2.5-Coder-32B share?
13 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Qwen2.5-Coder-32B has 31.