Model comparison
Magistral Medium vs Qwen2.5-Coder-32B
Magistral Medium is the stronger model overall, scoring 35.2 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Magistral Medium leads 39.1 to 22.6.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 33K.
Side by side
| Magistral Medium | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 33.4 |
| Released | 2025-03-17 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 16K | 29K |
| Input $ / M tokens | $2 | $0.66 |
| Output $ / M tokens | $5 | $1 |
| Results tracked | 22 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1319 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| SciCode | 39.2% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
Magistral Medium: 8.6 (#348), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1251 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1250 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge Too close to call
Magistral Medium: 33.5 (#202), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1223 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1232 | 1205 |
| LMArena Chinese | 1227 | 1222 |
| LMArena Russian | 1224 | 1228 |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1295 | 1251 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1255 | 1230 |
| LMArena Creative Writing | 1245 | 1174 |
| LMArena Multi-Turn | 1275 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Magistral Medium better than Qwen2.5-Coder-32B?
Magistral Medium is the stronger model overall, scoring 35.2 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, Magistral Medium or Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Qwen2.5-Coder-32B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 33K.
How many benchmarks do Magistral Medium and Qwen2.5-Coder-32B share?
12 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2.5-Coder-32B has 31.