# Kimi K2.5 vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.6 to 48.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-5-vs-muse-spark
- Last updated: 2026-10-11
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Kimi K2.5 scores higher in 3 categories and Muse Spark in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 53.6.
- The biggest single-benchmark swing is Humanity's Last Exam: 24.4% for Kimi K2.5 and 40.6% for Muse Spark.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2.5 | Muse Spark |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 48.1 | 50.6 |
| Rank | 57 | 46 |
| Context | 262K | — |
| Input $/M | $0.45 | — |
| Output $/M | $2.25 | — |
| Weights | Open | Proprietary |

## Coding

- Kimi K2.5: 48.8 (#53)
- Muse Spark: 46.2 (#69)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| SciCode | 49% | 51.5% |
| LMArena Coding | 1474 | 1481 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |

## Agentic & Tool Use

- Kimi K2.5: 34.2 (#48)
- Muse Spark: —

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |

## Reasoning

- Kimi K2.5: 31.2 (#80)
- Muse Spark: 35.9 (#67)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| CritPt | 3.1% | 11.3% |
| LMArena Hard Prompts | 1453 | 1474 |
| Epoch Capabilities Index | 148.03 | 152.04 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |

## Math

- Kimi K2.5: 51.8 (#53)
- Muse Spark: 47.8 (#66)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 88.9% |
| LMArena Math | 1470 | 1455 |
| FrontierMath (Feb 2025 set) | 27.9% | 39% |
| FrontierMath Tier 4 (v1) | 4.2% | 14.6% |
| MathArena Final-Answer Competitions | 62.3% | — |
| ProofBench | — | 17% |

## Knowledge

- Kimi K2.5: 53.6 (#56)
- Muse Spark: 65.7 (#13)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| GPQA Diamond | 87.6% | 89.8% |
| Humanity's Last Exam | 24.4% | 40.6% |
| LMArena Expert | 1466 | 1457 |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |

## Multimodal

- Kimi K2.5: 41.1 (#39)
- Muse Spark: 43.4 (#24)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| LMArena Vision | 1269 | 1306 |
| LMArena Document | 1430 | 1444 |

## Multilingual

- Kimi K2.5: 53.9 (#53)
- Muse Spark: 56.1 (#24)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1433 | 1464 |
| LMArena Chinese | 1495 | 1509 |
| LMArena French | 1454 | 1497 |
| LMArena German | 1441 | 1497 |
| LMArena Korean | 1410 | 1459 |
| LMArena Russian | 1435 | 1466 |
| LMArena Spanish | 1450 | 1472 |
| LMArena Japanese | 1421 | — |

## Instruction Following

- Kimi K2.5: 75.3 (#64)
- Muse Spark: 75.9 (#51)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1431 | 1442 |

## Long Context

- Kimi K2.5: 52.1 (#7)
- Muse Spark: 44.4 (#69)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1445 | 1451 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |

## Writing & Preference

- Kimi K2.5: 65.1 (#53)
- Muse Spark: 66.0 (#39)

| Benchmark | Kimi K2.5 | Muse Spark |
|---|---|---|
| LMArena Text | 1445 | 1474 |
| LMArena Creative Writing | 1423 | 1459 |
| LMArena Multi-Turn | 1444 | 1477 |
| EQ-Bench Creative Writing | 1579 | — |

## FAQ

### Is Kimi K2.5 better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 48.1 on the Noometry Index.

### Is Kimi K2.5 or Muse Spark better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 46.2 in the Noometry coding category.

### How many benchmarks do Kimi K2.5 and Muse Spark share?

26 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Muse Spark has 27.