Model comparison
Mistral vs Mixtral 8x7B
Mistral is the stronger model overall, scoring 29.9 to 27.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Mistral scores higher in 8 categories and Mixtral 8x7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral leads 16.6 to 11.0.
- The biggest single-benchmark swing is MMLU-Pro: 27.7% for Mistral and 33.5% for Mixtral 8x7B.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Mixtral 8x7B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 29.9 | 27.1 |
| Released | — | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 32K |
| Max output | — | 32K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 22 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Mistral: 33.8 (#250), Mixtral 8x7B: 32.8 (#269)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1162 | 1126 |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Reasoning Mistral leads
Mistral: 22.2 (#200), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1115 |
| 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 Mistral leads
Mistral: 22.3 (#278), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | 7.2% | 10.5% |
| LMArena Math | 1180 | 1147 |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge Mistral leads
Mistral: 16.6 (#288), Mixtral 8x7B: 11.0 (#301)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| MMLU-Pro | 27.7% | 33.5% |
| GPQA (HELM) | 30.3% | 29.6% |
| LMArena Expert | 1125 | 1088 |
| GPQA Diamond | — | 30.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual Mistral leads
Mistral: 32.8 (#254), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1129 | 1077 |
| LMArena Chinese | 1109 | 1055 |
| LMArena French | 1180 | 1166 |
| LMArena German | 1155 | 1114 |
| LMArena Japanese | 1013 | 931 |
| LMArena Korean | 1032 | 968 |
| LMArena Russian | 1168 | 1090 |
| LMArena Spanish | 1143 | 1111 |
Instruction Following Mistral leads
Mistral: 52.6 (#288), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| IFEval | 56.8% | 57.5% |
| LMArena Instruction Following | 1152 | 1109 |
Long Context Mistral leads
Mistral: 35.0 (#245), Mixtral 8x7B: 33.4 (#260)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1153 | 1103 |
Writing & Preference Mistral leads
Mistral: 37.0 (#260), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Mistral | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1165 | 1132 |
| LMArena Creative Writing | 1158 | 1109 |
| WildBench | 66% | 67.3% |
| LMArena Multi-Turn | 1147 | 1115 |
Frequently asked questions
Is Mistral better than Mixtral 8x7B?
Mistral is the stronger model overall, scoring 29.9 to 27.1 on the Noometry Index.
Is Mistral or Mixtral 8x7B better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 32.8 in the Noometry coding category.
How many benchmarks do Mistral and Mixtral 8x7B share?
22 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Mixtral 8x7B has 38.