Model comparison
Inkling vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 44.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. Inkling scores higher in 1 category and Muse Spark in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark leads 47.8 to 31.3.
- The biggest single-benchmark swing is ProofBench: 0% for Inkling and 17% for Muse Spark.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Muse Spark | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 50.6 |
| Released | 2026-07-15 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Inkling: 34.5 (#234), Muse Spark: 46.2 (#69)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| SciCode | 47% | 51.5% |
| LMArena Coding | 1464 | 1481 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Muse Spark: —
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Muse Spark: 35.9 (#67)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| CritPt | 5.4% | 11.3% |
| LMArena Hard Prompts | 1451 | 1474 |
| Epoch Capabilities Index | 148.54 | 152.04 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
Math Muse Spark leads
Inkling: 31.3 (#225), Muse Spark: 47.8 (#66)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 88.9% |
| ProofBench | 0% | 17% |
| LMArena Math | 1479 | 1455 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Inkling: 55.1 (#49), Muse Spark: 65.7 (#13)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| GPQA Diamond | 88.3% | 89.8% |
| LMArena Expert | 1465 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 40.3% | — |
Multimodal Not comparable
Inkling: —, Muse Spark: 43.4 (#24)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Inkling: 54.0 (#52), Muse Spark: 56.1 (#24)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Non-English | 1434 | 1464 |
| LMArena Chinese | 1490 | 1509 |
| LMArena French | 1458 | 1497 |
| LMArena German | 1446 | 1497 |
| LMArena Korean | 1404 | 1459 |
| LMArena Russian | 1429 | 1466 |
| LMArena Spanish | 1448 | 1472 |
| LMArena Japanese | 1429 | — |
Instruction Following Too close to call
Inkling: 75.1 (#71), Muse Spark: 75.9 (#51)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1426 | 1442 |
Long Context Too close to call
Inkling: 43.8 (#86), Muse Spark: 44.4 (#69)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1434 | 1451 |
Writing & Preference Too close to call
Inkling: 65.2 (#51), Muse Spark: 66.0 (#39)
| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Text | 1441 | 1474 |
| LMArena Creative Writing | 1387 | 1459 |
| LMArena Multi-Turn | 1436 | 1477 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 44.1 on the Noometry Index.
Is Inkling or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 34.5 in the Noometry coding category.
How many benchmarks do Inkling and Muse Spark share?
22 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Muse Spark has 27.