Model comparison
Claude 3 Haiku vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 25.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Claude 3 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 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 88.9% for Muse Spark.
Side by side
| Claude 3 Haiku | Muse Spark | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.9 | 50.6 |
| Released | 2024-03-07 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Claude 3 Haiku: 26.4 (#325), Muse Spark: 46.2 (#69)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| LMArena Coding | 1199 | 1481 |
| SciCode | — | 51.5% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Muse Spark leads
Claude 3 Haiku: 16.3 (#307), Muse Spark: 35.9 (#67)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1474 |
| Epoch Capabilities Index | 118.35 | 152.04 |
| Kagi LLM Benchmark | 34.2% | — |
| CritPt | — | 11.3% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Muse Spark leads
Claude 3 Haiku: 9.8 (#319), Muse Spark: 47.8 (#66)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 88.9% |
| LMArena Math | 1188 | 1455 |
| ProofBench | — | 17% |
| MATH Level 5 | 14.9% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Claude 3 Haiku: 17.3 (#285), Muse Spark: 65.7 (#13)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| GPQA Diamond | 36.3% | 89.8% |
| LMArena Expert | 1148 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Muse Spark leads
Claude 3 Haiku: 23.6 (#128), Muse Spark: 43.4 (#24)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| LMArena Vision | 950 | 1306 |
| LMArena Document | — | 1444 |
| ScienceQA | 72% | — |
Multilingual Muse Spark leads
Claude 3 Haiku: 36.0 (#243), Muse Spark: 56.1 (#24)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| LMArena Non-English | 1178 | 1464 |
| LMArena Chinese | 1155 | 1509 |
| LMArena French | 1195 | 1497 |
| LMArena German | 1174 | 1497 |
| LMArena Korean | 1109 | 1459 |
| LMArena Russian | 1204 | 1466 |
| LMArena Spanish | 1166 | 1472 |
| LMArena Japanese | 1102 | — |
Instruction Following Muse Spark leads
Claude 3 Haiku: 61.3 (#247), Muse Spark: 75.9 (#51)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1173 | 1442 |
Long Context Muse Spark leads
Claude 3 Haiku: 36.1 (#237), Muse Spark: 44.4 (#69)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1190 | 1451 |
Writing & Preference Muse Spark leads
Claude 3 Haiku: 29.7 (#291), Muse Spark: 66.0 (#39)
| Benchmark | Claude 3 Haiku | Muse Spark |
|---|---|---|
| LMArena Text | 1195 | 1474 |
| LMArena Creative Writing | 1157 | 1459 |
| LMArena Multi-Turn | 1190 | 1477 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Muse Spark share?
20 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Muse Spark has 27.