Model comparison
Mixtral 8x7B vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 27.1 on the Noometry Index. Mixtral 8x7B costs 2.9× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Mistral AI
MetaSummary
- They share 19 benchmarks with published results for both. Mixtral 8x7B scores higher in 0 categories and Muse Spark 1.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 18.8.
- The biggest single-benchmark swing is DTBench: 49.6% for Mixtral 8x7B and 96.5% for Muse Spark 1.3.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 32K.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x7B | Muse Spark 1.3 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 27.1 | 54.8 |
| Released | 2023-12-11 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 32K | 1.05M |
| Max output | 32K | 131K |
| Input $ / M tokens | $0.70 | $1.25 |
| Output $ / M tokens | $0.70 | $4.25 |
| Results tracked | 38 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Mixtral 8x7B: 32.8 (#269), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Coding | 1126 | 1514 |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
| SciCode | — | 59.7% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Agentic & Tool Use Not comparable
Mixtral 8x7B: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Mixtral 8x7B: 18.2 (#285), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1503 |
| DTBench | 49.6% | 96.5% |
| Epoch Capabilities Index | 118.47 | 156.75 |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 26% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| LMCA | — | 53.9% |
| Adversarial NLI | 55.2% | — |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Muse Spark 1.3 leads
Mixtral 8x7B: 18.8 (#289), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Math | 1147 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 58% |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Muse Spark 1.3 leads
Mixtral 8x7B: 11.0 (#301), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1088 | 1516 |
| 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% | — |
Multimodal Not comparable
Mixtral 8x7B: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
Mixtral 8x7B: 29.6 (#266), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1077 | 1481 |
| LMArena Chinese | 1055 | 1529 |
| LMArena French | 1166 | 1524 |
| LMArena German | 1114 | 1515 |
| LMArena Japanese | 931 | 1474 |
| LMArena Korean | 968 | 1501 |
| LMArena Russian | 1090 | 1490 |
| LMArena Spanish | 1111 | 1490 |
Instruction Following Muse Spark 1.3 leads
Mixtral 8x7B: 51.0 (#297), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1109 | 1477 |
| IFEval | 57.5% | — |
Long Context Muse Spark 1.3 leads
Mixtral 8x7B: 33.4 (#260), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1103 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Mixtral 8x7B: 34.2 (#270), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Mixtral 8x7B | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1132 | 1490 |
| LMArena Creative Writing | 1109 | 1455 |
| LMArena Multi-Turn | 1115 | 1482 |
| EQ-Bench Creative Writing | — | 1906 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 27.1 on the Noometry Index. Mixtral 8x7B costs 2.9× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, Mixtral 8x7B or Muse Spark 1.3?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Mixtral 8x7B or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 32K.
How many benchmarks do Mixtral 8x7B and Muse Spark 1.3 share?
19 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Muse Spark 1.3 has 37.