# Claude 3.5 Haiku vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.3 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-5-haiku-vs-muse-spark
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Muse Spark in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 18.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 88.9% for Muse Spark.

## Snapshot

| | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 28.9 | 50.3 |
| Rank | 309 | 41 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.5 Haiku: 32.6 (#258)
- Muse Spark: 45.6 (#65)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| SciCode | 27.4% | 51.5% |
| LMArena Coding | 1287 | 1482 |
| Aider Polyglot | 28% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |

## Agentic & Tool Use

- Claude 3.5 Haiku: 27.7 (#90)
- Muse Spark: —

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| BALROG | 19.3% | — |

## Reasoning

- Claude 3.5 Haiku: 17.1 (#286)
- Muse Spark: 34.9 (#61)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| CritPt | 0% | 11.3% |
| LMArena Hard Prompts | 1251 | 1475 |
| Epoch Capabilities Index | 127.15 | 152.09 |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| LiveBench | 43.5% | — |

## Math

- Claude 3.5 Haiku: 13.7 (#294)
- Muse Spark: 46.8 (#57)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 88.9% |
| LMArena Math | 1244 | 1455 |
| FrontierMath (Feb 2025 set) | 0.3% | 39% |
| ProofBench | — | 17% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- Claude 3.5 Haiku: 18.7 (#276)
- Muse Spark: 65.7 (#12)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| GPQA Diamond | 38.1% | 89.8% |
| LMArena Expert | 1208 | 1458 |
| Humanity's Last Exam | — | 40.6% |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |

## Multimodal

- Claude 3.5 Haiku: 26.3 (#113)
- Muse Spark: 42.7 (#23)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| LMArena Vision | 1092 | 1306 |
| GeoBench | 34% | — |
| LMArena Document | — | 1444 |

## Multilingual

- Claude 3.5 Haiku: 40.2 (#213)
- Muse Spark: 56.3 (#23)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| LMArena Non-English | 1238 | 1464 |
| LMArena Chinese | 1229 | 1507 |
| LMArena French | 1262 | 1497 |
| LMArena German | 1237 | 1497 |
| LMArena Korean | 1172 | 1457 |
| LMArena Russian | 1253 | 1467 |
| LMArena Spanish | 1261 | 1471 |
| LMArena Japanese | 1175 | — |

## Instruction Following

- Claude 3.5 Haiku: 63.1 (#229)
- Muse Spark: 76.1 (#47)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1241 | 1443 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |

## Long Context

- Claude 3.5 Haiku: 38.3 (#195)
- Muse Spark: 44.4 (#65)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1261 | 1451 |

## Writing & Preference

- Claude 3.5 Haiku: 42.9 (#228)
- Muse Spark: 66.2 (#37)

| Benchmark | Claude 3.5 Haiku | Muse Spark |
|---|---|---|
| LMArena Text | 1255 | 1474 |
| LMArena Creative Writing | 1233 | 1460 |
| LMArena Multi-Turn | 1265 | 1477 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |

## FAQ

### Is Claude 3.5 Haiku better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.3 to 28.9 on the Noometry Index.

### Is Claude 3.5 Haiku or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 45.6 versus 32.6 in the Noometry coding category.

### How many benchmarks do Claude 3.5 Haiku and Muse Spark share?

23 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Muse Spark has 27.