Model comparison
Grok 4.20 (Non-Reasoning) vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 48.6 on the Noometry Index.
Last verified . 30 shared benchmarks.
MetaSummary
- They share 30 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 1 category and Muse Spark 1.3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 48.2.
- The biggest single-benchmark swing is ProofBench: 14% for Grok 4.20 (Non-Reasoning) and 58% for Muse Spark 1.3.
- 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 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 1M.
Side by side
| Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.6 | 54.8 |
| Released | 2026-02-17 | 2026-09-02 |
| 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 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1375 | 1657 |
| LMArena Coding | 1459 | 1514 |
| CursorBench | — | 41.6% |
| SciCode | — | 59.7% |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 34.4 (#46), Muse Spark 1.3: 38.6 (#30)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| APEX-Agents | — | 57.8% |
| τ²-bench Banking | 18% | — |
| GDP.pdf | — | 27.6% |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 85.4% | 85.1% |
| Chess Puzzles | 24% | 38% |
| LMArena Hard Prompts | 1451 | 1503 |
| DTBench | 90.1% | 96.5% |
| LMCA | 38.7% | 53.9% |
| Epoch Capabilities Index | 151.98 | 156.75 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 89.5% | — |
| CritPt | — | 26% |
| Thematic Generalization | 63.8% | — |
| Mystery Game Puzzles | — | 25% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 61.4 | — |
Math Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 74.4% |
| FrontierMath Tier 4 | 17.1% | 46.3% |
| OTIS Mock AIME 2024-2025 | 92.2% | 99.2% |
| ProofBench | 14% | 58% |
| LMArena Math | 1455 | 1494 |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1439 | 1516 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
Multimodal Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 33.3 (#98), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1263 | 1309 |
| LMArena Document | 1416 | 1471 |
| Blueprint-Bench 2 | 0% | — |
Multilingual Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1441 | 1481 |
| LMArena Chinese | 1481 | 1529 |
| LMArena French | 1476 | 1524 |
| LMArena German | 1465 | 1515 |
| LMArena Japanese | 1449 | 1474 |
| LMArena Korean | 1417 | 1501 |
| LMArena Russian | 1458 | 1490 |
| LMArena Spanish | 1443 | 1490 |
Instruction Following Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1477 |
Long Context Too close to call
Grok 4.20 (Non-Reasoning): 45.5 (#34), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1437 | 1488 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Muse Spark 1.3 leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Grok 4.20 (Non-Reasoning) | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1451 | 1490 |
| LMArena Creative Writing | 1438 | 1455 |
| EQ-Bench Creative Writing | 1574 | 1906 |
| LMArena Multi-Turn | 1456 | 1482 |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 48.6 on the Noometry Index.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Muse Spark 1.3?
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 1.3 lists at $1.25 and $4.25.
Is Grok 4.20 (Non-Reasoning) or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 1M.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Muse Spark 1.3 share?
30 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Muse Spark 1.3 has 37.