Model comparison
Inkling-Small vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 46.5 on the Noometry Index. Inkling-Small costs 3.1× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Inkling-Small scores higher in 1 category and Muse Spark 1.3 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 45.1.
- The biggest single-benchmark swing is ProofBench: 6% for Inkling-Small and 58% for Muse Spark 1.3.
- Inkling-Small is cheaper at $0.45 / $1.20 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 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | Muse Spark 1.3 | |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 46.5 | 54.8 |
| Released | 2026-07-15 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 524K | 1.05M |
| Max output | 1.05M | 131K |
| Input $ / M tokens | $0.45 | $1.25 |
| Output $ / M tokens | $1.20 | $4.25 |
| Results tracked | 33 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Inkling-Small: 43.6 (#85), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1409 | 1657 |
| SciCode | 48.7% | 59.7% |
| LMArena Coding | 1451 | 1514 |
| CursorBench | — | 41.6% |
Agentic & Tool Use Not comparable
Inkling-Small: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Inkling-Small: 38.6 (#63), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| CritPt | 8.3% | 26% |
| Chess Puzzles | 18% | 38% |
| LMArena Hard Prompts | 1423 | 1503 |
| Mystery Game Puzzles | 6% | 25% |
| Epoch Capabilities Index | 150.15 | 156.75 |
| ARC-AGI-2 | 40.1% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 84% | — |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
Inkling-Small: 45.1 (#77), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 74.4% |
| FrontierMath Tier 4 | 17.1% | 46.3% |
| OTIS Mock AIME 2024-2025 | 90% | 99.2% |
| ProofBench | 6% | 58% |
| LMArena Math | 1459 | 1494 |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1442 | 1516 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
Multimodal Muse Spark 1.3 leads
Inkling-Small: 39.1 (#62), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1235 | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
Inkling-Small: 51.7 (#104), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1402 | 1481 |
| LMArena Chinese | 1465 | 1529 |
| LMArena French | 1436 | 1524 |
| LMArena German | 1405 | 1515 |
| LMArena Japanese | 1405 | 1474 |
| LMArena Korean | 1363 | 1501 |
| LMArena Russian | 1391 | 1490 |
| LMArena Spanish | 1428 | 1490 |
Instruction Following Muse Spark 1.3 leads
Inkling-Small: 73.8 (#114), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1477 |
Long Context Muse Spark 1.3 leads
Inkling-Small: 42.7 (#118), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1401 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Inkling-Small: 59.6 (#107), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Inkling-Small | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1414 | 1490 |
| LMArena Creative Writing | 1331 | 1455 |
| EQ-Bench Creative Writing | 1491 | 1906 |
| LMArena Multi-Turn | 1418 | 1482 |
Frequently asked questions
Is Inkling-Small better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 46.5 on the Noometry Index. Inkling-Small costs 3.1× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Muse Spark 1.3?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Inkling-Small or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 524K.
How many benchmarks do Inkling-Small and Muse Spark 1.3 share?
29 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Muse Spark 1.3 has 37.