Model comparison
Magistral Medium vs Qwen-14B
Magistral Medium is the stronger model overall, scoring 35.2 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Magistral Medium scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Magistral Medium leads 46.3 to 27.6.
Side by side
| Magistral Medium | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 31.4 |
| Released | 2025-03-17 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Qwen-14B: 31.2 (#288)
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Coding | 1319 | 1071 |
| SciCode | 39.2% | — |
Reasoning Qwen-14B leads
Magistral Medium: 8.6 (#348), Qwen-14B: 19.6 (#257)
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1027 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Qwen-14B: 31.2 (#227)
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Math | 1250 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Magistral Medium: 33.5 (#202), Qwen-14B: —
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Expert | 1223 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Qwen-14B: 27.5 (#275)
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1232 | 1041 |
| LMArena Chinese | 1227 | 1077 |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Russian | 1224 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Qwen-14B: 52.4 (#289)
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1031 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Qwen-14B: 31.3 (#280)
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1295 | 1028 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Qwen-14B: 27.6 (#299)
| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Text | 1255 | 1051 |
| LMArena Creative Writing | 1245 | 1028 |
| LMArena Multi-Turn | 1275 | 1022 |
Frequently asked questions
Is Magistral Medium better than Qwen-14B?
Magistral Medium is the stronger model overall, scoring 35.2 to 31.4 on the Noometry Index.
Is Magistral Medium or Qwen-14B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 31.2 in the Noometry coding category.
How many benchmarks do Magistral Medium and Qwen-14B share?
10 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen-14B has 18.