Model comparison
Mixtral 8x7B vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 27.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Mixtral 8x7B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Max leads 35.3 to 11.0.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x7B | Qwen2.5-Max | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 40.7 |
| Released | 2023-12-11 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Mixtral 8x7B: 32.8 (#269), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1126 | 1359 |
| LiveBench Coding | — | 64.4% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Qwen2.5-Max leads
Mixtral 8x7B: 18.2 (#285), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1360 |
| Epoch Capabilities Index | 118.47 | 132.53 |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 49.6% | — |
| LiveBench Data Analysis | — | 67.9% |
| Adversarial NLI | 55.2% | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| LiveBench | — | 62.3% |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Qwen2.5-Max leads
Mixtral 8x7B: 18.8 (#289), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1147 | 1369 |
| Omni-MATH | 10.5% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Qwen2.5-Max leads
Mixtral 8x7B: 11.0 (#301), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1088 | 1337 |
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| Confabulations | — | 21.8% |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Qwen2.5-Max leads
Mixtral 8x7B: 29.6 (#266), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1077 | 1352 |
| LMArena Chinese | 1055 | 1382 |
| LMArena French | 1166 | 1396 |
| LMArena German | 1114 | 1350 |
| LMArena Japanese | 931 | 1300 |
| LMArena Korean | 968 | 1304 |
| LMArena Russian | 1090 | 1353 |
| LMArena Spanish | 1111 | 1377 |
Instruction Following Qwen2.5-Max leads
Mixtral 8x7B: 51.0 (#297), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1109 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 57.5% | — |
Long Context Qwen2.5-Max leads
Mixtral 8x7B: 33.4 (#260), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1103 | 1358 |
Writing & Preference Qwen2.5-Max leads
Mixtral 8x7B: 34.2 (#270), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Mixtral 8x7B | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1132 | 1367 |
| LMArena Creative Writing | 1109 | 1339 |
| LMArena Multi-Turn | 1115 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| WildBench | 67.3% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Mixtral 8x7B better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 27.1 on the Noometry Index.
Is Mixtral 8x7B or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 32.8 in the Noometry coding category.
How many benchmarks do Mixtral 8x7B and Qwen2.5-Max share?
18 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen2.5-Max has 27.