Model comparison
Mixtral 8x7B vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 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 Qwen1.5-110B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-110B leads 31.2 to 11.0.
Side by side
| Mixtral 8x7B | Qwen1.5-110B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 34.2 |
| Released | 2023-12-11 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mixtral 8x7B: 32.8 (#269), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1126 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Qwen1.5-110B leads
Mixtral 8x7B: 18.2 (#285), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1168 |
| ForecastBench | 56.3 | 57.7 |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.47 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Qwen1.5-110B leads
Mixtral 8x7B: 18.8 (#289), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1147 | 1185 |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Qwen1.5-110B leads
Mixtral 8x7B: 11.0 (#301), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1088 | 1144 |
| 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 Qwen1.5-110B leads
Mixtral 8x7B: 29.6 (#266), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1077 | 1142 |
| LMArena Chinese | 1055 | 1206 |
| LMArena French | 1166 | 1151 |
| LMArena German | 1114 | 1123 |
| LMArena Japanese | 931 | 1074 |
| LMArena Korean | 968 | 1044 |
| LMArena Russian | 1090 | 1118 |
| LMArena Spanish | 1111 | 1142 |
Instruction Following Qwen1.5-110B leads
Mixtral 8x7B: 51.0 (#297), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1109 | 1158 |
| IFEval | 57.5% | — |
Long Context Qwen1.5-110B leads
Mixtral 8x7B: 33.4 (#260), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1103 | 1157 |
Writing & Preference Qwen1.5-110B leads
Mixtral 8x7B: 34.2 (#270), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Mixtral 8x7B | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1132 | 1175 |
| LMArena Creative Writing | 1109 | 1148 |
| LMArena Multi-Turn | 1115 | 1160 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 27.1 on the Noometry Index.
Is Mixtral 8x7B or Qwen1.5-110B better for coding?
They score almost the same on coding (32.8 vs 33.0); test both on your own repository before choosing.
How many benchmarks do Mixtral 8x7B and Qwen1.5-110B share?
18 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen1.5-110B has 20.