# Inkling vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.3 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-vs-muse-spark
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- 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 46.8 to 31.2.
- 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.

## Snapshot

| | Inkling | Muse Spark |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 44.1 | 50.3 |
| Rank | 75 | 41 |
| Context | 66K | — |
| Input $/M | $1.87 | — |
| Output $/M | $4.68 | — |
| Weights | Open | Proprietary |

## Coding

- Inkling: 34.1 (#229)
- Muse Spark: 45.6 (#65)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| SciCode | 47% | 51.5% |
| LMArena Coding | 1463 | 1482 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |

## Agentic & Tool Use

- Inkling: 29.5 (#76)
- Muse Spark: —

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.6 (#48)
- Muse Spark: 34.9 (#61)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| CritPt | 5.4% | 11.3% |
| LMArena Hard Prompts | 1452 | 1475 |
| Epoch Capabilities Index | 148.6 | 152.09 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |

## Math

- Inkling: 31.2 (#198)
- Muse Spark: 46.8 (#57)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 88.9% |
| ProofBench | 0% | 17% |
| LMArena Math | 1482 | 1455 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- Inkling: 55.2 (#44)
- Muse Spark: 65.7 (#12)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| GPQA Diamond | 88.3% | 89.8% |
| LMArena Expert | 1468 | 1458 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 40.3% | — |

## Multimodal

- Inkling: —
- Muse Spark: 42.7 (#23)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- Inkling: 54.2 (#49)
- Muse Spark: 56.3 (#23)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Non-English | 1434 | 1464 |
| LMArena Chinese | 1495 | 1507 |
| LMArena French | 1453 | 1497 |
| LMArena German | 1456 | 1497 |
| LMArena Korean | 1401 | 1457 |
| LMArena Russian | 1430 | 1467 |
| LMArena Spanish | 1442 | 1471 |
| LMArena Japanese | 1428 | — |

## Instruction Following

- Inkling: 75.3 (#65)
- Muse Spark: 76.1 (#47)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1427 | 1443 |

## Long Context

- Inkling: 43.9 (#79)
- Muse Spark: 44.4 (#65)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1436 | 1451 |

## Writing & Preference

- Inkling: 65.5 (#48)
- Muse Spark: 66.2 (#37)

| Benchmark | Inkling | Muse Spark |
|---|---|---|
| LMArena Text | 1443 | 1474 |
| LMArena Creative Writing | 1390 | 1460 |
| LMArena Multi-Turn | 1436 | 1477 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.3 to 44.1 on the Noometry Index.

### Is Inkling or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 45.6 versus 34.1 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.