Model comparison
Mistral vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral scores higher in 2 categories and Qwen3-30B-A3B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.8 to 16.6.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 38.9 |
| Released | — | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | — | 41K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.12 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 22 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Mistral: 33.8 (#250), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1162 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
Agentic & Tool Use Not comparable
Mistral: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Too close to call
Mistral: 22.2 (#200), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
Math Qwen3-30B-A3B leads
Mistral: 22.3 (#278), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1180 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| Omni-MATH | 7.2% | — |
Knowledge Qwen3-30B-A3B leads
Mistral: 16.6 (#288), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1125 | 1396 |
| GPQA Diamond | — | 70.1% |
| MMLU-Pro | 27.7% | — |
| Confabulations | — | 12.3% |
| GPQA (HELM) | 30.3% | — |
Multilingual Qwen3-30B-A3B leads
Mistral: 32.8 (#254), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1129 | 1372 |
| LMArena Chinese | 1109 | 1433 |
| LMArena French | 1180 | 1418 |
| LMArena German | 1155 | 1380 |
| LMArena Japanese | 1013 | 1337 |
| LMArena Korean | 1032 | 1331 |
| LMArena Russian | 1168 | 1370 |
| LMArena Spanish | 1143 | 1404 |
Instruction Following Qwen3-30B-A3B leads
Mistral: 52.6 (#288), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1363 |
| IFEval | 56.8% | — |
Long Context Mistral leads
Mistral: 35.0 (#245), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1153 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Mistral: 37.0 (#260), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Mistral | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1165 | 1384 |
| LMArena Creative Writing | 1158 | 1317 |
| LMArena Multi-Turn | 1147 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.9 on the Noometry Index.
Is Mistral or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 33.8 in the Noometry coding category.
How many benchmarks do Mistral and Qwen3-30B-A3B share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen3-30B-A3B has 32.