Model comparison
Mistral Medium vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 36.3 on the Noometry Index.
Last verified . 27 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Mistral Medium scores higher in 5 categories and Qwen3-30B-A3B in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.8 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 70.3% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 41K.
Side by side
| Mistral Medium | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 38.9 |
| Released | 2023-12-11 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 262K | 41K |
| Max output | 262K | 16K |
| Input $ / M tokens | $1.50 | $0.12 |
| Output $ / M tokens | $7.50 | $0.50 |
| Results tracked | 36 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Mistral Medium: 34.2 (#243), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 40.2% | 33.3% |
| WeirdML | 43.7% | 29.8% |
| LMArena Coding | 1434 | 1416 |
| FrontierCode | 8% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Qwen3-30B-A3B leads
Mistral Medium: 28.3 (#90), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | 41.4% |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 50% | 54.9% |
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1426 | 1398 |
| DTBench | 75.5% | 69.3% |
| LMCA | 26.1% | 22.4% |
| Chess Puzzles | — | 8% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 139.63 |
Math Qwen3-30B-A3B leads
Mistral Medium: 28.1 (#245), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 70.3% |
| LMArena Math | 1408 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3-30B-A3B leads
Mistral Medium: 25.0 (#265), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 59.5% | 70.1% |
| LMArena Expert | 1408 | 1396 |
| Humanity's Last Exam | 4.5% | — |
| Confabulations | — | 12.3% |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Qwen3-30B-A3B: —
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1408 | 1372 |
| LMArena Chinese | 1447 | 1433 |
| LMArena French | 1459 | 1418 |
| LMArena German | 1432 | 1380 |
| LMArena Japanese | 1378 | 1337 |
| LMArena Korean | 1380 | 1331 |
| LMArena Russian | 1411 | 1370 |
| LMArena Spanish | 1433 | 1404 |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1398 | 1363 |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1406 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Mistral Medium | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1424 | 1384 |
| LMArena Creative Writing | 1391 | 1317 |
| Short-Story Creative Writing | 77.3% | 75.3% |
| LMArena Multi-Turn | 1418 | 1378 |
Frequently asked questions
Is Mistral Medium better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 36.3 on the Noometry Index.
Which is cheaper, Mistral 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; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 41K.
How many benchmarks do Mistral Medium and Qwen3-30B-A3B share?
27 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3-30B-A3B has 32.