Model comparison
Magistral Small vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 30.2 on the Noometry Index.
Last verified . 8 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Magistral Small scores higher in 1 category and Qwen3-30B-A3B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-30B-A3B leads 22.2 to 6.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 6.3% for Magistral Small and 54.9% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Magistral Small accepts more context: 128K tokens versus 41K.
Side by side
| Magistral Small | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.2 | 38.9 |
| Released | 2025-06-10 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 128K | 41K |
| Max output | 40K | 16K |
| Input $ / M tokens | $0.50 | $0.12 |
| Output $ / M tokens | $1.50 | $0.50 |
| Results tracked | 10 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Magistral Small: 38.4 (#176), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 35.2% | 33.3% |
| WeirdML | — | 29.8% |
| LMArena Coding | — | 1416 |
Agentic & Tool Use Not comparable
Magistral Small: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Qwen3-30B-A3B leads
Magistral Small: 6.8 (#350), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 6.3% | 54.9% |
| CritPt | 0.3% | 0.3% |
| Chess Puzzles | 3% | 8% |
| DTBench | 61.3% | 69.3% |
| Epoch Capabilities Index | 133.19 | 139.63 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 5% | — |
| LMArena Hard Prompts | — | 1398 |
| LMCA | — | 22.4% |
Math Qwen3-30B-A3B leads
Magistral Small: 26.2 (#261), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | 70.3% |
| MathArena Final-Answer Competitions | — | 47.8% |
| LMArena Math | — | 1394 |
Knowledge Qwen3-30B-A3B leads
Magistral Small: 30.9 (#223), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 56.1% | 70.1% |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1396 |
Multilingual Not comparable
Magistral Small: —, Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1433 |
| LMArena French | — | 1418 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
| LMArena Russian | — | 1370 |
| LMArena Spanish | — | 1404 |
Instruction Following Not comparable
Magistral Small: —, Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | — | 1363 |
Long Context Not comparable
Magistral Small: —, Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | — | 40.6% |
| LMArena Longer Query | — | 1379 |
Writing & Preference Not comparable
Magistral Small: —, Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Magistral Small | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | — | 1384 |
| LMArena Creative Writing | — | 1317 |
| Short-Story Creative Writing | — | 75.3% |
| LMArena Multi-Turn | — | 1378 |
Frequently asked questions
Is Magistral Small better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 30.2 on the Noometry Index.
Which is cheaper, Magistral Small 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 Small lists at $0.50 and $1.50.
Is Magistral Small or Qwen3-30B-A3B better for coding?
They score almost the same on coding (38.4 vs 37.5); test both on your own repository before choosing.
Which has the bigger context window?
Magistral Small does, with 128K tokens against 41K.
How many benchmarks do Magistral Small and Qwen3-30B-A3B share?
8 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Qwen3-30B-A3B has 32.