Model comparison
Magistral Medium vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 35.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Magistral Medium scores higher in 1 category and Qwen3-Coder 480B-A35B Instruct in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-Coder 480B-A35B Instruct leads 25.5 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
Side by side
| Magistral Medium | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 38.1 |
| Released | 2025-03-17 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $5 | $7.50 |
| Results tracked | 22 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Coding | 1319 | 1412 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| SciCode | 39.2% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Magistral Medium: 8.6 (#348), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 49.5% |
| LMArena Hard Prompts | 1267 | 1372 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math Qwen3-Coder 480B-A35B Instruct leads
Magistral Medium: 35.1 (#189), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1250 | 1365 |
Knowledge Qwen3-Coder 480B-A35B Instruct leads
Magistral Medium: 33.5 (#202), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1223 | 1338 |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Magistral Medium: 39.6 (#224), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1232 | 1346 |
| LMArena Chinese | 1227 | 1357 |
| LMArena French | 1267 | 1398 |
| LMArena German | 1248 | 1325 |
| LMArena Japanese | 1175 | 1310 |
| LMArena Korean | 1125 | 1305 |
| LMArena Russian | 1224 | 1366 |
| LMArena Spanish | 1271 | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Magistral Medium: 66.0 (#211), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1254 | 1355 |
Long Context Qwen3-Coder 480B-A35B Instruct leads
Magistral Medium: 39.3 (#183), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1295 | 1378 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Magistral Medium: 46.3 (#219), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1255 | 1357 |
| LMArena Creative Writing | 1245 | 1333 |
| LMArena Multi-Turn | 1275 | 1365 |
Frequently asked questions
Is Magistral Medium better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen3-Coder 480B-A35B Instruct?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Magistral Medium or Qwen3-Coder 480B-A35B Instruct better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Magistral Medium and Qwen3-Coder 480B-A35B Instruct share?
18 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.