# DeepSeek-V2.5 (Sep 2024) vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-muse-spark-1-2
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Muse Spark 1.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 24.5.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 37.0 | 49.8 |
| Rank | 197 | 44 |
| Context | — | 1.05M |
| Input $/M | — | $1.25 |
| Output $/M | — | $4.25 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Muse Spark 1.2: 48.6 (#49)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Coding | 1310 | 1497 |
| DeepSWE | — | 54.9% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1532 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- Muse Spark 1.2: 29.5 (#77)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Muse Spark 1.2: 50.4 (#32)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1490 |
| SimpleBench | — | 74.5% |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 155.18 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Muse Spark 1.2: 43.8 (#68)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |
| LMArena Math | 1289 | — |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Muse Spark 1.2: 53.9 (#49)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1266 | 1485 |
| SimpleQA Verified | — | 60.3% |

## Multimodal

- DeepSeek-V2.5 (Sep 2024): —
- Muse Spark 1.2: 42.6 (#24)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Muse Spark 1.2: 57.4 (#10)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1273 | 1479 |
| LMArena Chinese | 1317 | 1519 |
| LMArena Russian | 1289 | 1494 |
| LMArena French | 1288 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Muse Spark 1.2: 77.1 (#30)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1466 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Muse Spark 1.2: 45.4 (#35)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1301 | 1483 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Muse Spark 1.2: 72.6 (#14)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1294 | 1486 |
| LMArena Creative Writing | 1285 | 1444 |
| LMArena Multi-Turn | 1297 | 1504 |
| EQ-Bench Creative Writing | — | 1840 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Muse Spark 1.2 share?

11 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Muse Spark 1.2 has 28.