# Claude Haiku 4.5 vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.3 to 39.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-muse-spark
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and Muse Spark in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 37.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.7% for Claude Haiku 4.5 and 88.9% for Muse Spark.

## Snapshot

| | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 39.3 | 50.3 |
| Rank | 155 | 41 |
| Context | 200K | — |
| Input $/M | $1 | — |
| Output $/M | $5 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 4.5: 43.9 (#71)
- Muse Spark: 45.6 (#65)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| SciCode | 43.3% | 51.5% |
| LMArena Coding | 1454 | 1482 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.5 (#50)
- Muse Spark: —

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#310)
- Muse Spark: 34.9 (#61)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| CritPt | 0% | 11.3% |
| LMArena Hard Prompts | 1420 | 1475 |
| Epoch Capabilities Index | 142.42 | 152.09 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| ForecastBench | 61.4 | — |

## Math

- Claude Haiku 4.5: 43.0 (#69)
- Muse Spark: 46.8 (#57)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 88.9% |
| LMArena Math | 1395 | 1455 |
| FrontierMath (Feb 2025 set) | 5.9% | 39% |
| FrontierMath Tier 4 (v1) | 2.1% | 14.6% |
| ProofBench | — | 17% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |

## Knowledge

- Claude Haiku 4.5: 37.6 (#146)
- Muse Spark: 65.7 (#12)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| GPQA Diamond | 71.2% | 89.8% |
| LMArena Expert | 1443 | 1458 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 27.0 (#111)
- Muse Spark: 42.7 (#23)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| LMArena Document | 1420 | 1444 |
| LMArena Vision | — | 1306 |
| Blueprint-Bench 2 | 0% | — |

## Multilingual

- Claude Haiku 4.5: 50.1 (#124)
- Muse Spark: 56.3 (#23)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1376 | 1464 |
| LMArena Chinese | 1415 | 1507 |
| LMArena French | 1408 | 1497 |
| LMArena German | 1377 | 1497 |
| LMArena Korean | 1346 | 1457 |
| LMArena Russian | 1380 | 1467 |
| LMArena Spanish | 1420 | 1471 |
| LMArena Japanese | 1339 | — |

## Instruction Following

- Claude Haiku 4.5: 71.6 (#144)
- Muse Spark: 76.1 (#47)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1414 | 1443 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#86)
- Muse Spark: 44.4 (#65)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1427 | 1451 |

## Writing & Preference

- Claude Haiku 4.5: 58.1 (#119)
- Muse Spark: 66.2 (#37)

| Benchmark | Claude Haiku 4.5 | Muse Spark |
|---|---|---|
| LMArena Text | 1396 | 1474 |
| LMArena Creative Writing | 1371 | 1460 |
| LMArena Multi-Turn | 1409 | 1477 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.3 to 39.3 on the Noometry Index.

### Is Claude Haiku 4.5 or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 45.6 versus 43.9 in the Noometry coding category.

### How many benchmarks do Claude Haiku 4.5 and Muse Spark share?

24 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Muse Spark has 27.