Model comparison
Mixtral 8x7B vs Pixtral Large
Pixtral Large is the stronger model overall, scoring 32.2 to 27.1 on the Noometry Index. Mixtral 8x7B costs 4.3× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where Pixtral Large leads 21.7 to 18.2.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Pixtral Large accepts more context: 128K tokens versus 32K.
Side by side
| Mixtral 8x7B | Pixtral Large | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 27.1 | 32.2 |
| Released | 2023-12-11 | 2024-11-01 |
| Weights | Open | Open |
| Context window | 32K | 128K |
| Max output | 32K | 128K |
| Input $ / M tokens | $0.70 | $2 |
| Output $ / M tokens | $0.70 | $6 |
| Results tracked | 38 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mixtral 8x7B: 32.8 (#269), Pixtral Large: —
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| LMArena Coding | 1126 | — |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Pixtral Large leads
Mixtral 8x7B: 18.2 (#285), Pixtral Large: 21.7 (#218)
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| EnigmaEval | — | 0.8% |
| LMArena Hard Prompts | 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 Not comparable
Mixtral 8x7B: 18.8 (#289), Pixtral Large: —
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| Omni-MATH | 10.5% | — |
| LMArena Math | 1147 | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Not comparable
Mixtral 8x7B: 11.0 (#301), Pixtral Large: —
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| LMArena Expert | 1088 | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multimodal Not comparable
Mixtral 8x7B: —, Pixtral Large: 30.6 (#111)
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |
Multilingual Not comparable
Mixtral 8x7B: 29.6 (#266), Pixtral Large: —
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1077 | — |
| LMArena Chinese | 1055 | — |
| LMArena French | 1166 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
| LMArena Russian | 1090 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Not comparable
Mixtral 8x7B: 51.0 (#297), Pixtral Large: —
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| IFEval | 57.5% | — |
| LMArena Instruction Following | 1109 | — |
Long Context Not comparable
Mixtral 8x7B: 33.4 (#260), Pixtral Large: —
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1103 | — |
Writing & Preference Mixtral 8x7B leads
Mixtral 8x7B: 34.2 (#270), Pixtral Large: 32.9 (#278)
| Benchmark | Mixtral 8x7B | Pixtral Large |
|---|---|---|
| LMArena Text | 1132 | — |
| LMArena Creative Writing | 1109 | — |
| EQ-Bench Creative Writing | — | 988 |
| WildBench | 67.3% | — |
| LMArena Multi-Turn | 1115 | — |
Frequently asked questions
Is Mixtral 8x7B better than Pixtral Large?
Pixtral Large is the stronger model overall, scoring 32.2 to 27.1 on the Noometry Index. Mixtral 8x7B costs 4.3× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Which is cheaper, Mixtral 8x7B or Pixtral Large?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Pixtral Large does, with 128K tokens against 32K.
How many benchmarks do Mixtral 8x7B and Pixtral Large share?
0 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Pixtral Large has 3.