Model comparison
Magistral Medium vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 35.2 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Qwen3 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 33.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 69.4% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 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 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 35.2 | 43.5 |
| Released | 2025-03-17 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 16K | 16K |
| Input $ / M tokens | $2 | $0.70 |
| Output $ / M tokens | $5 | $2.80 |
| Results tracked | 22 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Magistral Medium: 39.1 (#161), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 39.2% | 42.4% |
| LMArena Coding | 1319 | 1445 |
| Aider Polyglot | — | 59.6% |
| WeirdML | — | 41% |
Agentic & Tool Use Not comparable
Magistral Medium: —, Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen3 235B-A22B leads
Magistral Medium: 8.6 (#348), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 0% | 1.3% |
| Kagi LLM Benchmark | 16.2% | 69.4% |
| ARC-AGI-1 | 6.1% | 11% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1267 | 1433 |
| SimpleBench | — | 31% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.85 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Magistral Medium: 35.1 (#189), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1250 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Magistral Medium: 33.5 (#202), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| LMArena Expert | 1223 | 1463 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multilingual Qwen3 235B-A22B leads
Magistral Medium: 39.6 (#224), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1232 | 1409 |
| LMArena Chinese | 1227 | 1481 |
| LMArena French | 1267 | 1445 |
| LMArena German | 1248 | 1433 |
| LMArena Japanese | 1175 | 1399 |
| LMArena Korean | 1125 | 1391 |
| LMArena Russian | 1224 | 1411 |
| LMArena Spanish | 1271 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Magistral Medium: 66.0 (#211), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Magistral Medium: 39.3 (#183), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1295 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Magistral Medium: 46.3 (#219), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Magistral Medium | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1255 | 1419 |
| LMArena Creative Writing | 1245 | 1384 |
| LMArena Multi-Turn | 1275 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
Frequently asked questions
Is Magistral Medium better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Qwen3 235B-A22B?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 39.1 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 Qwen3 235B-A22B share?
22 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3 235B-A22B has 49.