Model comparison
Mixtral 8x7B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 27.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Mixtral 8x7B scores higher in 1 category and Qwen3-30B-A3B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.8 to 11.0.
- The biggest single-benchmark swing is GPQA Diamond: 30.6% for Mixtral 8x7B and 70.1% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- Qwen3-30B-A3B accepts more context: 41K tokens versus 32K.
Side by side
| Mixtral 8x7B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 38.9 |
| Released | 2023-12-11 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 32K | 41K |
| Max output | 32K | 16K |
| Input $ / M tokens | $0.70 | $0.12 |
| Output $ / M tokens | $0.70 | $0.50 |
| Results tracked | 38 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Mixtral 8x7B: 32.8 (#269), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1126 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Agentic & Tool Use Not comparable
Mixtral 8x7B: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Qwen3-30B-A3B leads
Mixtral 8x7B: 18.2 (#285), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1398 |
| DTBench | 49.6% | 69.3% |
| Epoch Capabilities Index | 118.47 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| LMCA | — | 22.4% |
| Adversarial NLI | 55.2% | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Qwen3-30B-A3B leads
Mixtral 8x7B: 18.8 (#289), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1147 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Qwen3-30B-A3B leads
Mixtral 8x7B: 11.0 (#301), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 30.6% | 70.1% |
| LMArena Expert | 1088 | 1396 |
| MMLU-Pro | 33.5% | — |
| Confabulations | — | 12.3% |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Qwen3-30B-A3B leads
Mixtral 8x7B: 29.6 (#266), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1077 | 1372 |
| LMArena Chinese | 1055 | 1433 |
| LMArena French | 1166 | 1418 |
| LMArena German | 1114 | 1380 |
| LMArena Japanese | 931 | 1337 |
| LMArena Korean | 968 | 1331 |
| LMArena Russian | 1090 | 1370 |
| LMArena Spanish | 1111 | 1404 |
Instruction Following Qwen3-30B-A3B leads
Mixtral 8x7B: 51.0 (#297), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1109 | 1363 |
| IFEval | 57.5% | — |
Long Context Mixtral 8x7B leads
Mixtral 8x7B: 33.4 (#260), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1103 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Mixtral 8x7B: 34.2 (#270), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Mixtral 8x7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1132 | 1384 |
| LMArena Creative Writing | 1109 | 1317 |
| LMArena Multi-Turn | 1115 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 27.1 on the Noometry Index.
Which is cheaper, Mixtral 8x7B 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; Mixtral 8x7B lists at $0.70 and $0.70.
Is Mixtral 8x7B or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3-30B-A3B does, with 41K tokens against 32K.
How many benchmarks do Mixtral 8x7B and Qwen3-30B-A3B share?
20 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen3-30B-A3B has 32.