# Kimi K2.6 vs Muse Spark 1.3

> Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 47.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-6-vs-muse-spark-1-3
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Kimi K2.6 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 agentic & tool use, where Muse Spark 1.3 leads 38.6 to 21.8.
- The biggest single-benchmark swing is FrontierMath Tier 4: 25.6% for Kimi K2.6 and 46.3% for Muse Spark 1.3.
- Kimi K2.6 is cheaper at $0.95 / $4 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 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 47.5 | 54.4 |
| Rank | 52 | 27 |
| Context | 262K | 1.05M |
| Input $/M | $0.95 | $1.25 |
| Output $/M | $4 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- Kimi K2.6: 50.5 (#41)
- Muse Spark 1.3: 56.1 (#18)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1509 | 1655 |
| SciCode | 53.5% | 59.7% |
| LMArena Coding | 1488 | 1516 |
| SWE-bench Verified | 76.7% | — |
| CursorBench | — | 41.6% |
| WeirdML | 55.9% | — |
| ALE-Bench | 1,093 | — |

## Agentic & Tool Use

- Kimi K2.6: 21.8 (#128)
- Muse Spark 1.3: 38.6 (#28)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| GDP.pdf | 12% | 27.6% |
| APEX-Agents | — | 57.8% |
| OSWorld 2.0 | 4.6% | — |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 6,205 | — |

## Reasoning

- Kimi K2.6: 39.6 (#51)
- Muse Spark 1.3: 52.9 (#27)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 87.2% | 85.1% |
| CritPt | 8% | 24.9% |
| Chess Puzzles | 26% | 38% |
| LMArena Hard Prompts | 1470 | 1503 |
| Mystery Game Puzzles | 18% | 25% |
| DTBench | 90.9% | 96.5% |
| LMCA | 37.3% | 53.9% |
| Epoch Capabilities Index | 151.03 | 156.89 |
| EBR-Bench | 2.4% | — |
| Bench to the Future 3 | — | 0.14 |

## Math

- Kimi K2.6: 56.8 (#34)
- Muse Spark 1.3: 72.4 (#16)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.2% | 74.4% |
| FrontierMath Tier 4 | 25.6% | 46.3% |
| OTIS Mock AIME 2024-2025 | 96.1% | 99.2% |
| LMArena Math | 1475 | 1497 |
| MathArena Final-Answer Competitions | 72.9% | — |
| ProofBench | 16% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Kimi K2.6: 53.9 (#48)
- Muse Spark 1.3: 42.0 (#92)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1491 | 1516 |
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |
| Vectara Hallucination Rate | 10.8% | — |

## Multimodal

- Kimi K2.6: 31.8 (#95)
- Muse Spark 1.3: 43.0 (#21)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1282 | 1310 |
| LMArena Document | 1451 | 1471 |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |

## Multilingual

- Kimi K2.6: 55.1 (#35)
- Muse Spark 1.3: 57.8 (#6)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1446 | 1485 |
| LMArena Chinese | 1521 | 1527 |
| LMArena French | 1471 | 1534 |
| LMArena Korean | 1428 | 1513 |
| LMArena Russian | 1446 | 1491 |
| LMArena Spanish | 1463 | 1485 |
| LMArena German | 1449 | — |
| LMArena Japanese | 1442 | — |

## Instruction Following

- Kimi K2.6: 76.5 (#40)
- Muse Spark 1.3: 77.8 (#14)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1481 |

## Long Context

- Kimi K2.6: 44.9 (#50)
- Muse Spark 1.3: 45.7 (#29)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1468 | 1491 |

## Writing & Preference

- Kimi K2.6: 68.7 (#25)
- Muse Spark 1.3: 73.7 (#10)

| Benchmark | Kimi K2.6 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1455 | 1490 |
| LMArena Creative Writing | 1434 | 1450 |
| EQ-Bench Creative Writing | 1725 | 1906 |
| LMArena Multi-Turn | 1453 | 1486 |
| EQ-Bench 4 | 1202 | — |

## FAQ

### Is Kimi K2.6 better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 47.5 on the Noometry Index.

### Which is cheaper, Kimi K2.6 or Muse Spark 1.3?

Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.

### Is Kimi K2.6 or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 50.5 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 262K.

### How many benchmarks do Kimi K2.6 and Muse Spark 1.3 share?

31 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Muse Spark 1.3 has 34.