Model comparison
Qwen2.5-Coder-32B vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 3.2× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 Max leads 62.4 to 41.6.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-Coder-32B | Qwen3 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 33.4 | 43.7 |
| Released | 2024-09-18 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 33K | 262K |
| Max output | 29K | 66K |
| Input $ / M tokens | $0.66 | $1.20 |
| Output $ / M tokens | $1 | $6 |
| Results tracked | 31 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Qwen2.5-Coder-32B: 22.6 (#333), Qwen3 Max: 43.0 (#93)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1276 | 1456 |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| BigCodeBench Complete | 58% | — |
| ALE-Bench | — | 370.45 |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |
Agentic & Tool Use Not comparable
Qwen2.5-Coder-32B: —, Qwen3 Max: —
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
Qwen2.5-Coder-32B: 21.2 (#225), Qwen3 Max: 22.6 (#190)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1448 |
| Epoch Capabilities Index | 119.49 | 142.38 |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 42.1% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LiveBench Data Analysis | 49.9% | — |
| LMCA | — | 28.3% |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |
Math Qwen3 Max leads
Qwen2.5-Coder-32B: 33.3 (#204), Qwen3 Max: 38.7 (#131)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Math | 1251 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | 46.6% | — |
| MATH Level 5 | — | 97.1% |
| GSM8K | 93% | — |
Knowledge Qwen3 Max leads
Qwen2.5-Coder-32B: 33.4 (#203), Qwen3 Max: 48.1 (#78)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1221 | 1455 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |
Multilingual Qwen3 Max leads
Qwen2.5-Coder-32B: 37.8 (#235), Qwen3 Max: 53.7 (#62)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1205 | 1429 |
| LMArena Chinese | 1222 | 1478 |
| LMArena Russian | 1228 | 1428 |
| LMArena French | — | 1449 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1397 |
| LMArena Korean | — | 1399 |
| LMArena Spanish | — | 1462 |
Instruction Following Qwen3 Max leads
Qwen2.5-Coder-32B: 61.4 (#245), Qwen3 Max: 74.8 (#87)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1223 | 1419 |
| LiveBench Instruction Following | 58.7% | — |
Long Context Qwen3 Max leads
Qwen2.5-Coder-32B: 38.0 (#208), Qwen3 Max: 41.6 (#134)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1251 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Qwen2.5-Coder-32B: 41.6 (#240), Qwen3 Max: 62.4 (#76)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 Max |
|---|---|---|
| LMArena Text | 1230 | 1439 |
| LMArena Creative Writing | 1174 | 1402 |
| LMArena Multi-Turn | 1222 | 1446 |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 3.2× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen2.5-Coder-32B or Qwen3 Max?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Qwen2.5-Coder-32B or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 33K.
How many benchmarks do Qwen2.5-Coder-32B and Qwen3 Max share?
13 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Qwen3 Max has 33.