# Claude 3 Haiku vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-muse-spark-1-2
- Last updated: 2026-10-12
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Muse Spark 1.2 leads 72.3 to 29.7.
- The biggest single-benchmark swing is WeirdML: 9.8% for Claude 3 Haiku and 60.3% for Muse Spark 1.2.

## Snapshot

| | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.9 | 50.3 |
| Rank | 340 | 48 |
| Context | — | 1.05M |
| Input $/M | — | $1.25 |
| Output $/M | — | $4.25 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Muse Spark 1.2: 49.2 (#51)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| WeirdML | 9.8% | 60.3% |
| LMArena Coding | 1199 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Muse Spark 1.2: 29.4 (#87)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Muse Spark 1.2: 51.3 (#34)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1486 |
| DTBench | 50.1% | 94.7% |
| LMCA | 8.8% | 48.4% |
| Epoch Capabilities Index | 118.35 | 154.87 |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Muse Spark 1.2: 46.4 (#70)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1188 | 1471 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| ProofBench | — | 43% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Muse Spark 1.2: 54.1 (#53)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1148 | 1480 |
| GPQA Diamond | 36.3% | — |
| SimpleQA Verified | — | 60.3% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Muse Spark 1.2: 43.4 (#25)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 950 | 1305 |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Muse Spark 1.2: 57.1 (#11)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1178 | 1478 |
| LMArena Chinese | 1155 | 1511 |
| LMArena French | 1195 | 1513 |
| LMArena Russian | 1204 | 1487 |
| LMArena Spanish | 1166 | 1498 |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Muse Spark 1.2: 76.7 (#36)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1461 |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Muse Spark 1.2: 45.2 (#48)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1190 | 1475 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Muse Spark 1.2: 72.3 (#14)

| Benchmark | Claude 3 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1195 | 1482 |
| LMArena Creative Writing | 1157 | 1449 |
| EQ-Bench Creative Writing | 717 | 1840 |
| LMArena Multi-Turn | 1190 | 1494 |

## FAQ

### Is Claude 3 Haiku better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Muse Spark 1.2 share?

20 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Muse Spark 1.2 has 31.