Model comparison
Grok 4.20 (Non-Reasoning) vs Muse Spark 1.1
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 48.5 on the Noometry Index.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 5 categories and Muse Spark 1.1 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Muse Spark 1.1 leads 50.8 to 41.8.
- The biggest single-benchmark swing is SimpleQA Verified: 30.2% for Grok 4.20 (Non-Reasoning) and 57.8% for Muse Spark 1.1.
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 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 1M.
Side by side
| Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.5 | 49.9 |
| Released | 2026-02-17 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 30K | 131K |
| Input $ / M tokens | $1.25 | $1.25 |
| Output $ / M tokens | $2.50 | $4.25 |
| Results tracked | 46 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.1 leads
Grok 4.20 (Non-Reasoning): 41.8 (#104), Muse Spark 1.1: 50.8 (#38)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| LMArena WebDev | 1374 | 1542 |
| LMArena Coding | 1458 | 1497 |
| DeepSWE | — | 53.3% |
| SciCode | — | 58.8% |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Too close to call
Grok 4.20 (Non-Reasoning): 34.3 (#43), Muse Spark 1.1: 33.9 (#45)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| τ²-bench Banking | 18% | 40.5% |
| Vending-Bench 2 | 4,663 | 6,520 |
| Terminal-Bench | 57.3% | — |
| GBAEval | — | 7.9% |
| GDP.pdf | — | 15% |
| LMArena Search | 1189 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.2 (#30), Muse Spark 1.1: 45.9 (#41)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| NYT Connections (extended) | 85.4% | 84.9% |
| LMArena Hard Prompts | 1451 | 1486 |
| DTBench | 90.1% | 94.4% |
| LMCA | 38.7% | 49.9% |
| Epoch Capabilities Index | 152.01 | 154.32 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 89.5% | — |
| CritPt | — | 15.1% |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| Surface Evolver Bench | — | 52.5% |
| ForecastBench | 61.4 | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.0 (#54), Muse Spark 1.1: 44.0 (#67)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| ProofBench | 14% | 39% |
| LMArena Math | 1455 | 1477 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
Knowledge Too close to call
Grok 4.20 (Non-Reasoning): 52.8 (#54), Muse Spark 1.1: 52.8 (#55)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| SimpleQA Verified | 30.2% | 57.8% |
| LMArena Expert | 1440 | 1480 |
| GPQA Diamond | 89.3% | — |
Multimodal Muse Spark 1.1 leads
Grok 4.20 (Non-Reasoning): 33.2 (#88), Muse Spark 1.1: 41.9 (#28)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | 1263 | 1292 |
| LMArena Document | 1416 | 1465 |
| Blueprint-Bench 2 | 0% | — |
Multilingual Muse Spark 1.1 leads
Grok 4.20 (Non-Reasoning): 54.7 (#38), Muse Spark 1.1: 56.8 (#16)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1440 | 1471 |
| LMArena Chinese | 1481 | 1518 |
| LMArena French | 1477 | 1494 |
| LMArena German | 1463 | 1466 |
| LMArena Japanese | 1450 | 1445 |
| LMArena Korean | 1417 | 1459 |
| LMArena Russian | 1457 | 1482 |
| LMArena Spanish | 1442 | 1471 |
Instruction Following Muse Spark 1.1 leads
Grok 4.20 (Non-Reasoning): 75.0 (#79), Muse Spark 1.1: 76.8 (#36)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1457 |
Long Context Too close to call
Grok 4.20 (Non-Reasoning): 45.4 (#33), Muse Spark 1.1: 44.8 (#55)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1436 | 1463 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Muse Spark 1.1 leads
Grok 4.20 (Non-Reasoning): 65.9 (#42), Muse Spark 1.1: 73.6 (#11)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1451 | 1479 |
| LMArena Creative Writing | 1439 | 1440 |
| EQ-Bench Creative Writing | 1574 | 1927 |
| LMArena Multi-Turn | 1456 | 1484 |
| EQ-Bench 4 | — | 1260 |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Muse Spark 1.1?
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 48.5 on the Noometry Index.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Muse Spark 1.1?
Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is Grok 4.20 (Non-Reasoning) or Muse Spark 1.1 better for coding?
Muse Spark 1.1 scores higher on coding benchmarks: 50.8 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 1M.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Muse Spark 1.1 share?
29 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Muse Spark 1.1 has 36.