Model comparison
Magistral Medium vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 34.8 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Magistral Medium scores higher in 2 categories and Qwen3-30B-A3B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-30B-A3B leads 21.6 to 8.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 54.9% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 128K tokens versus 41K.
Side by side
| Magistral Medium | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 38.5 |
| Released | 2025-03-17 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 128K | 41K |
| Max output | 16K | 16K |
| Input $ / M tokens | $2 | $0.12 |
| Output $ / M tokens | $5 | $0.50 |
| Results tracked | 22 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 38.6 (#161), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 39.2% | 33.3% |
| LMArena Coding | 1319 | 1416 |
| WeirdML | — | 29.8% |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Qwen3-30B-A3B leads
Magistral Medium: 8.7 (#342), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 54.9% |
| CritPt | 0.3% | 0.3% |
| LMArena Hard Prompts | 1267 | 1398 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 6.1% | — |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
Math Qwen3-30B-A3B leads
Magistral Medium: 32.4 (#187), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1249 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
Knowledge Qwen3-30B-A3B leads
Magistral Medium: 32.9 (#199), Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1222 | 1395 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
Multilingual Qwen3-30B-A3B leads
Magistral Medium: 39.8 (#219), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1232 | 1372 |
| LMArena Chinese | 1225 | 1434 |
| LMArena French | 1268 | 1419 |
| LMArena German | 1248 | 1379 |
| LMArena Japanese | 1176 | 1338 |
| LMArena Korean | 1125 | 1333 |
| LMArena Russian | 1224 | 1369 |
| LMArena Spanish | 1269 | 1403 |
Instruction Following Qwen3-30B-A3B leads
Magistral Medium: 66.2 (#207), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1364 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#178), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1295 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Magistral Medium: 46.5 (#214), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | Magistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1255 | 1384 |
| LMArena Creative Writing | 1245 | 1318 |
| LMArena Multi-Turn | 1275 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is Magistral Medium better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 34.8 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Qwen3-30B-A3B better for coding?
Magistral Medium scores higher on coding benchmarks: 38.6 versus 37.0 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 128K tokens against 41K.
How many benchmarks do Magistral Medium and Qwen3-30B-A3B share?
20 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3-30B-A3B has 32.