# DeepSeek-V2.5 (Sep 2024) vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.3 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-muse-spark
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 34.2.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 37.0 | 50.3 |
| Rank | 197 | 41 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Muse Spark: 45.6 (#65)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Coding | 1310 | 1482 |
| Aider Polyglot | 17.8% | — |
| SciCode | — | 51.5% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Muse Spark: 34.9 (#61)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1475 |
| CritPt | — | 11.3% |
| Epoch Capabilities Index | — | 152.09 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Muse Spark: 46.8 (#57)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Math | 1289 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Muse Spark: 65.7 (#12)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Expert | 1266 | 1458 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |

## Multimodal

- DeepSeek-V2.5 (Sep 2024): —
- Muse Spark: 42.7 (#23)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Muse Spark: 56.3 (#23)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Non-English | 1273 | 1464 |
| LMArena Chinese | 1317 | 1507 |
| LMArena French | 1288 | 1497 |
| LMArena German | 1258 | 1497 |
| LMArena Korean | 1209 | 1457 |
| LMArena Russian | 1289 | 1467 |
| LMArena Spanish | 1248 | 1471 |
| LMArena Japanese | 1228 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Muse Spark: 76.1 (#47)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1280 | 1443 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Muse Spark: 44.4 (#65)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1301 | 1451 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Muse Spark: 66.2 (#37)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark |
|---|---|---|
| LMArena Text | 1294 | 1474 |
| LMArena Creative Writing | 1285 | 1460 |
| LMArena Multi-Turn | 1297 | 1477 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.3 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 45.6 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Muse Spark share?

16 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Muse Spark has 27.