Model comparison
Mixtral 8x7B vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 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 Qwen2.5-Coder-32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 33.4 to 11.0.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B accepts more context: 33K tokens versus 32K.
Side by side
| Mixtral 8x7B | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 33.4 |
| Released | 2023-12-11 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 32K | 33K |
| Max output | 32K | 29K |
| Input $ / M tokens | $0.70 | $0.66 |
| Output $ / M tokens | $0.70 | $1 |
| Results tracked | 38 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
Mixtral 8x7B: 32.8 (#269), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1126 | 1276 |
| HumanEval+ | 39.6% | 87.2% |
| MBPP+ | 49.7% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
Reasoning Qwen2.5-Coder-32B leads
Mixtral 8x7B: 18.2 (#285), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1251 |
| Epoch Capabilities Index | 118.47 | 119.49 |
| HellaSwag | 86.7% | 83% |
| WinoGrande | 77.2% | 80.8% |
| LiveBench Reasoning | — | 42.1% |
| DTBench | 49.6% | — |
| LiveBench Data Analysis | — | 49.9% |
| Adversarial NLI | 55.2% | — |
| ForecastBench | 56.3 | — |
| LiveBench | — | 46.2% |
| PIQA | 83.6% | — |
Math Qwen2.5-Coder-32B leads
Mixtral 8x7B: 18.8 (#289), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1147 | 1251 |
| GSM8K | 74.4% | 93% |
| Omni-MATH | 10.5% | — |
| LiveBench Math | — | 46.6% |
| MATH Level 5 | 10% | — |
Knowledge Qwen2.5-Coder-32B leads
Mixtral 8x7B: 11.0 (#301), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1088 | 1221 |
| ARC (AI2) Challenge | 87.3% | 70.5% |
| MMLU | 70.6% | 79.1% |
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Qwen2.5-Coder-32B leads
Mixtral 8x7B: 29.6 (#266), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1077 | 1205 |
| LMArena Chinese | 1055 | 1222 |
| LMArena Russian | 1090 | 1228 |
| LMArena French | 1166 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Qwen2.5-Coder-32B leads
Mixtral 8x7B: 51.0 (#297), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1109 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
| IFEval | 57.5% | — |
Long Context Qwen2.5-Coder-32B leads
Mixtral 8x7B: 33.4 (#260), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1103 | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
Mixtral 8x7B: 34.2 (#270), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Mixtral 8x7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1132 | 1230 |
| LMArena Creative Writing | 1109 | 1174 |
| LMArena Multi-Turn | 1115 | 1222 |
| WildBench | 67.3% | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Mixtral 8x7B better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 27.1 on the Noometry Index.
Which is cheaper, Mixtral 8x7B or Qwen2.5-Coder-32B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is Mixtral 8x7B or Qwen2.5-Coder-32B better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5-Coder-32B does, with 33K tokens against 32K.
How many benchmarks do Mixtral 8x7B and Qwen2.5-Coder-32B share?
20 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen2.5-Coder-32B has 31.