Model comparison
Inkling vs Muse Spark 1.1
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 44.1 on the Noometry Index.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Inkling scores higher in 1 category and Muse Spark 1.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Muse Spark 1.1 leads 51.3 to 34.5.
- The biggest single-benchmark swing is ProofBench: 0% for Inkling and 39% for Muse Spark 1.1.
- Muse Spark 1.1 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Muse Spark 1.1 | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 49.9 |
| Released | 2026-07-15 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 66K | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $1.87 | $1.25 |
| Output $ / M tokens | $4.68 | $4.25 |
| Results tracked | 41 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.1 leads
Inkling: 34.5 (#234), Muse Spark 1.1: 51.3 (#40)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| LMArena WebDev | 1413 | 1542 |
| SciCode | 47% | 58.8% |
| LMArena Coding | 1464 | 1498 |
| DeepSWE | — | 53.3% |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Muse Spark 1.1 leads
Inkling: 29.6 (#85), Muse Spark 1.1: 30.8 (#73)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| APEX-Agents | 33.8% | 31.8% |
| τ²-bench Banking | 25% | 40.5% |
| GBAEval | — | 7.9% |
| GDP.pdf | — | 15% |
| Vending-Bench 2 | — | 6,520 |
Reasoning Muse Spark 1.1 leads
Inkling: 40.4 (#56), Muse Spark 1.1: 47.1 (#44)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| CritPt | 5.4% | 15.1% |
| LMArena Hard Prompts | 1451 | 1486 |
| DTBench | 87.5% | 94.4% |
| LMCA | 37.6% | 49.9% |
| Epoch Capabilities Index | 148.54 | 154.21 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 84.9% |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| Surface Evolver Bench | — | 52.5% |
Math Muse Spark 1.1 leads
Inkling: 31.3 (#225), Muse Spark 1.1: 45.5 (#76)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| ProofBench | 0% | 39% |
| LMArena Math | 1479 | 1483 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), Muse Spark 1.1: 53.1 (#59)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| SimpleQA Verified | 40.3% | 57.8% |
| LMArena Expert | 1465 | 1478 |
| GPQA Diamond | 88.3% | — |
Multimodal Not comparable
Inkling: —, Muse Spark 1.1: 42.6 (#29)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | — | 1293 |
| LMArena Document | — | 1465 |
Multilingual Muse Spark 1.1 leads
Inkling: 54.0 (#52), Muse Spark 1.1: 56.7 (#17)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1434 | 1472 |
| LMArena Chinese | 1490 | 1518 |
| LMArena French | 1458 | 1494 |
| LMArena German | 1446 | 1466 |
| LMArena Japanese | 1429 | 1451 |
| LMArena Korean | 1404 | 1458 |
| LMArena Russian | 1429 | 1483 |
| LMArena Spanish | 1448 | 1464 |
Instruction Following Muse Spark 1.1 leads
Inkling: 75.1 (#71), Muse Spark 1.1: 76.5 (#39)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1457 |
Long Context Too close to call
Inkling: 43.8 (#86), Muse Spark 1.1: 44.8 (#58)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1434 | 1462 |
Writing & Preference Muse Spark 1.1 leads
Inkling: 65.2 (#51), Muse Spark 1.1: 73.4 (#11)
| Benchmark | Inkling | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1441 | 1479 |
| LMArena Creative Writing | 1387 | 1437 |
| EQ-Bench Creative Writing | 1611 | 1927 |
| EQ-Bench 4 | 1226 | 1260 |
| LMArena Multi-Turn | 1436 | 1485 |
Frequently asked questions
Is Inkling better than Muse Spark 1.1?
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 44.1 on the Noometry Index.
Which is cheaper, Inkling or Muse Spark 1.1?
Muse Spark 1.1 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Muse Spark 1.1 better for coding?
Muse Spark 1.1 scores higher on coding benchmarks: 51.3 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 66K.
How many benchmarks do Inkling and Muse Spark 1.1 share?
29 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Muse Spark 1.1 has 37.