Model comparison
Mixtral 8x7B vs Qwen1.5 4b Chat
Qwen1.5 4b Chat is the stronger model overall, scoring 28.8 to 27.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Mixtral 8x7B scores higher in 5 categories and Qwen1.5 4b Chat in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5 4b Chat leads 26.7 to 11.0.
Side by side
| Mixtral 8x7B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 28.8 |
| Released | 2023-12-11 | — |
| Weights | Open | Open |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
Mixtral 8x7B: 32.8 (#269), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1126 | 999 |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Too close to call
Mixtral 8x7B: 18.2 (#285), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1115 | 976 |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.47 | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Qwen1.5 4b Chat leads
Mixtral 8x7B: 18.8 (#289), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1147 | 1026 |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Qwen1.5 4b Chat leads
Mixtral 8x7B: 11.0 (#301), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1088 | 980 |
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Mixtral 8x7B leads
Mixtral 8x7B: 29.6 (#266), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1077 | 979 |
| LMArena Chinese | 1055 | 1024 |
| LMArena German | 1114 | 902 |
| LMArena Russian | 1090 | 952 |
| LMArena French | 1166 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Mixtral 8x7B leads
Mixtral 8x7B: 51.0 (#297), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1109 | 978 |
| IFEval | 57.5% | — |
Long Context Mixtral 8x7B leads
Mixtral 8x7B: 33.4 (#260), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1103 | 988 |
Writing & Preference Mixtral 8x7B leads
Mixtral 8x7B: 34.2 (#270), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Mixtral 8x7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1132 | 997 |
| LMArena Creative Writing | 1109 | 969 |
| LMArena Multi-Turn | 1115 | 977 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Qwen1.5 4b Chat?
Qwen1.5 4b Chat is the stronger model overall, scoring 28.8 to 27.1 on the Noometry Index.
Is Mixtral 8x7B or Qwen1.5 4b Chat better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 29.1 in the Noometry coding category.
How many benchmarks do Mixtral 8x7B and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen1.5 4b Chat has 13.