Model comparison
Magistral Medium vs Qwen2.5 72B Instruct
Magistral Medium is the stronger model overall, scoring 35.2 to 31.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 5 categories and Qwen2.5 72B Instruct in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 19.3.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 131K.
Side by side
| Magistral Medium | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 31.9 |
| Released | 2025-03-17 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 16K | 8K |
| Input $ / M tokens | $2 | $1.40 |
| Output $ / M tokens | $5 | $5.60 |
| Results tracked | 22 | 43 |
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 72B Instruct: 33.2 (#260)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1319 | 1292 |
| SciCode | 39.2% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Magistral Medium: 8.6 (#348), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1271 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1250 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1223 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Qwen2.5 72B Instruct leads
Magistral Medium: 39.6 (#224), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1232 | 1252 |
| LMArena Chinese | 1227 | 1272 |
| LMArena French | 1267 | 1280 |
| LMArena German | 1248 | 1234 |
| LMArena Japanese | 1175 | 1180 |
| LMArena Korean | 1125 | 1188 |
| LMArena Russian | 1224 | 1264 |
| LMArena Spanish | 1271 | 1256 |
Instruction Following Too close to call
Magistral Medium: 66.0 (#211), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1254 | 1254 |
| IFEval | — | 80.6% |
Long Context Too close to call
Magistral Medium: 39.3 (#183), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1295 | 1282 |
Writing & Preference Too close to call
Magistral Medium: 46.3 (#219), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Magistral Medium | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1255 | 1269 |
| LMArena Creative Writing | 1245 | 1221 |
| LMArena Multi-Turn | 1275 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Magistral Medium better than Qwen2.5 72B Instruct?
Magistral Medium is the stronger model overall, scoring 35.2 to 31.9 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Qwen2.5 72B Instruct better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 131K.
How many benchmarks do Magistral Medium and Qwen2.5 72B Instruct share?
17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2.5 72B Instruct has 43.