Model comparison
Llama 4 Scout vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 27.4 on the Noometry Index. Llama 4 Scout costs 13× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Muse Spark 1.3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 72.4 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 99.2% for Muse Spark 1.3.
- Llama 4 Scout is cheaper at $0.10 / $0.30 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 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Muse Spark 1.3 | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 27.4 | 54.4 |
| Released | 2025-04-05 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.10 | $1.25 |
| Output $ / M tokens | $0.30 | $4.25 |
| Results tracked | 43 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Llama 4 Scout: 19.9 (#334), Muse Spark 1.3: 56.1 (#18)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| SciCode | 17% | 59.7% |
| LMArena Coding | 1286 | 1516 |
| SWE-bench Verified (bash only) | 9.1% | — |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1655 |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Muse Spark 1.3 leads
Llama 4 Scout: 24.4 (#109), Muse Spark 1.3: 38.6 (#28)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 28.1% | — |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Llama 4 Scout: 9.2 (#339), Muse Spark 1.3: 52.9 (#27)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| CritPt | 0% | 24.9% |
| LMArena Hard Prompts | 1266 | 1503 |
| DTBench | 57.9% | 96.5% |
| LMCA | 12% | 53.9% |
| Epoch Capabilities Index | 129.64 | 156.89 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 0.5% | — |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 57.5 | — |
Math Muse Spark 1.3 leads
Llama 4 Scout: 18.4 (#280), Muse Spark 1.3: 72.4 (#16)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 99.2% |
| LMArena Math | 1286 | 1497 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Muse Spark 1.3 leads
Llama 4 Scout: 31.8 (#208), Muse Spark 1.3: 42.0 (#92)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1236 | 1516 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Muse Spark 1.3 leads
Llama 4 Scout: 31.6 (#98), Muse Spark 1.3: 43.0 (#21)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1118 | 1310 |
| LMArena Document | — | 1471 |
| SpatialViz-Bench | 34.2% | — |
Multilingual Muse Spark 1.3 leads
Llama 4 Scout: 41.3 (#207), Muse Spark 1.3: 57.8 (#6)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1253 | 1485 |
| LMArena Chinese | 1256 | 1527 |
| LMArena French | 1283 | 1534 |
| LMArena Korean | 1207 | 1513 |
| LMArena Russian | 1263 | 1491 |
| LMArena Spanish | 1277 | 1485 |
| LMArena German | 1274 | — |
| LMArena Japanese | 1209 | — |
Instruction Following Muse Spark 1.3 leads
Llama 4 Scout: 66.0 (#212), Muse Spark 1.3: 77.8 (#14)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1481 |
| IFEval | 81.8% | — |
Long Context Muse Spark 1.3 leads
Llama 4 Scout: 27.5 (#289), Muse Spark 1.3: 45.7 (#29)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1265 | 1491 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Muse Spark 1.3 leads
Llama 4 Scout: 37.1 (#256), Muse Spark 1.3: 73.7 (#10)
| Benchmark | Llama 4 Scout | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1279 | 1490 |
| LMArena Creative Writing | 1249 | 1450 |
| EQ-Bench Creative Writing | 783 | 1906 |
| LMArena Multi-Turn | 1281 | 1486 |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 27.4 on the Noometry Index. Llama 4 Scout costs 13× 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, Llama 4 Scout or Muse Spark 1.3?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Llama 4 Scout or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 128K.
How many benchmarks do Llama 4 Scout and Muse Spark 1.3 share?
23 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Muse Spark 1.3 has 34.