Model comparison
Qwen2.5-Coder-32B vs Qwen3-VL 235B-A22B
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 1.6× less per token, which makes it the better buy when Qwen3-VL 235B-A22B's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 0 categories and Qwen3-VL 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3-VL 235B-A22B leads 42.4 to 22.6.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $0.70 / $2.80 for Qwen3-VL 235B-A22B.
- Qwen3-VL 235B-A22B accepts more context: 131K tokens versus 33K.
Side by side
| Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 33.4 | 43.2 |
| Released | 2024-09-18 | 2025-04 |
| Weights | Open | Open |
| Context window | 33K | 131K |
| Max output | 29K | 33K |
| Input $ / M tokens | $0.66 | $0.70 |
| Output $ / M tokens | $1 | $2.80 |
| Results tracked | 31 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 22.6 (#333), Qwen3-VL 235B-A22B: 42.4 (#100)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Coding | 1276 | 1439 |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |
Reasoning Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 21.2 (#225), Qwen3-VL 235B-A22B: 29.3 (#92)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1428 |
| LiveBench Reasoning | 42.1% | — |
| LiveBench Data Analysis | 49.9% | — |
| Epoch Capabilities Index | 119.49 | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |
Math Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 33.3 (#204), Qwen3-VL 235B-A22B: 39.0 (#118)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Math | 1251 | 1426 |
| LiveBench Math | 46.6% | — |
| GSM8K | 93% | — |
Knowledge Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 33.4 (#203), Qwen3-VL 235B-A22B: 40.3 (#121)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Expert | 1221 | 1442 |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |
Multimodal Not comparable
Qwen2.5-Coder-32B: —, Qwen3-VL 235B-A22B: 39.8 (#55)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 37.8 (#235), Qwen3-VL 235B-A22B: 51.9 (#97)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Non-English | 1205 | 1405 |
| LMArena Chinese | 1222 | 1463 |
| LMArena Russian | 1228 | 1408 |
| LMArena French | — | 1452 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1385 |
| LMArena Korean | — | 1394 |
| LMArena Spanish | — | 1428 |
Instruction Following Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 61.4 (#245), Qwen3-VL 235B-A22B: 74.2 (#101)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1223 | 1406 |
| LiveBench Instruction Following | 58.7% | — |
Long Context Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 38.0 (#208), Qwen3-VL 235B-A22B: 43.4 (#98)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1251 | 1420 |
Writing & Preference Qwen3-VL 235B-A22B leads
Qwen2.5-Coder-32B: 41.6 (#240), Qwen3-VL 235B-A22B: 60.2 (#99)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Text | 1230 | 1420 |
| LMArena Creative Writing | 1174 | 1366 |
| LMArena Multi-Turn | 1222 | 1428 |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than Qwen3-VL 235B-A22B?
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 1.6× less per token, which makes it the better buy when Qwen3-VL 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Qwen2.5-Coder-32B or Qwen3-VL 235B-A22B?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Qwen3-VL 235B-A22B lists at $0.70 and $2.80.
Is Qwen2.5-Coder-32B or Qwen3-VL 235B-A22B better for coding?
Qwen3-VL 235B-A22B scores higher on coding benchmarks: 42.4 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3-VL 235B-A22B does, with 131K tokens against 33K.
How many benchmarks do Qwen2.5-Coder-32B and Qwen3-VL 235B-A22B share?
12 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Qwen3-VL 235B-A22B has 18.