Model comparison
Llama 4 Maverick vs Muse Spark 1.1
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 30.6 on the Noometry Index. Llama 4 Maverick costs 6.6× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
MetaSummary
- They share 25 benchmarks with published results for both. Llama 4 Maverick scores higher in 0 categories and Muse Spark 1.1 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.1 leads 45.9 to 10.1.
- The biggest single-benchmark swing is NYT Connections (extended): 8% for Llama 4 Maverick and 84.9% for Muse Spark 1.1.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | Muse Spark 1.1 | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.6 | 49.9 |
| Released | 2025-04-05 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.19 | $1.25 |
| Output $ / M tokens | $0.65 | $4.25 |
| Results tracked | 54 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.1 leads
Llama 4 Maverick: 26.3 (#318), Muse Spark 1.1: 50.8 (#38)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| SciCode | 33.1% | 58.8% |
| LMArena Coding | 1302 | 1497 |
| DeepSWE | — | 53.3% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| LMArena WebDev | — | 1542 |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Muse Spark 1.1 leads
Llama 4 Maverick: 27.9 (#86), Muse Spark 1.1: 33.9 (#45)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
| τ²-bench Banking | — | 40.5% |
| GBAEval | — | 7.9% |
| GDP.pdf | — | 15% |
| Vending-Bench 2 | — | 6,520 |
Reasoning Muse Spark 1.1 leads
Llama 4 Maverick: 10.1 (#337), Muse Spark 1.1: 45.9 (#41)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| NYT Connections (extended) | 8% | 84.9% |
| CritPt | 0% | 15.1% |
| LMArena Hard Prompts | 1281 | 1486 |
| DTBench | 61.9% | 94.4% |
| LMCA | 15.9% | 49.9% |
| Epoch Capabilities Index | 132.2 | 154.32 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| ARC-AGI-1 | 4.4% | — |
| EnigmaEval | 0.6% | — |
| Surface Evolver Bench | — | 52.5% |
| ForecastBench | 57.5 | — |
Math Muse Spark 1.1 leads
Llama 4 Maverick: 24.6 (#256), Muse Spark 1.1: 44.0 (#67)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| LMArena Math | 1299 | 1477 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| ProofBench | — | 39% |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Muse Spark 1.1 leads
Llama 4 Maverick: 33.3 (#196), Muse Spark 1.1: 52.8 (#55)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| LMArena Expert | 1259 | 1480 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| SimpleQA Verified | — | 57.8% |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Muse Spark 1.1 leads
Llama 4 Maverick: 30.9 (#100), Muse Spark 1.1: 41.9 (#28)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | 1141 | 1292 |
| GeoBench | 52% | — |
| LMArena Document | — | 1465 |
| SpatialViz-Bench | 31.8% | — |
Multilingual Muse Spark 1.1 leads
Llama 4 Maverick: 42.4 (#190), Muse Spark 1.1: 56.8 (#16)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1269 | 1471 |
| LMArena Chinese | 1277 | 1518 |
| LMArena French | 1258 | 1494 |
| LMArena German | 1291 | 1466 |
| LMArena Japanese | 1207 | 1445 |
| LMArena Korean | 1203 | 1459 |
| LMArena Russian | 1286 | 1482 |
| LMArena Spanish | 1293 | 1471 |
Instruction Following Muse Spark 1.1 leads
Llama 4 Maverick: 71.9 (#140), Muse Spark 1.1: 76.8 (#36)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1267 | 1457 |
| IFEval | 90.8% | — |
Long Context Muse Spark 1.1 leads
Llama 4 Maverick: 31.4 (#274), Muse Spark 1.1: 44.8 (#55)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1280 | 1463 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Muse Spark 1.1 leads
Llama 4 Maverick: 39.0 (#247), Muse Spark 1.1: 73.6 (#11)
| Benchmark | Llama 4 Maverick | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1287 | 1479 |
| LMArena Creative Writing | 1266 | 1440 |
| EQ-Bench Creative Writing | 860 | 1927 |
| LMArena Multi-Turn | 1289 | 1484 |
| Short-Story Creative Writing | 62% | — |
| WildBench | 80% | — |
| EQ-Bench 4 | — | 1260 |
Frequently asked questions
Is Llama 4 Maverick better than Muse Spark 1.1?
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 30.6 on the Noometry Index. Llama 4 Maverick costs 6.6× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Maverick or Muse Spark 1.1?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is Llama 4 Maverick or Muse Spark 1.1 better for coding?
Muse Spark 1.1 scores higher on coding benchmarks: 50.8 versus 26.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 128K.
How many benchmarks do Llama 4 Maverick and Muse Spark 1.1 share?
25 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Muse Spark 1.1 has 36.