Model comparison
Claude 3.5 Haiku vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 29.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Muse Spark 1.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark 1.2 leads 54.1 to 18.7.
- The biggest single-benchmark swing is DTBench: 56.7% for Claude 3.5 Haiku and 94.7% for Muse Spark 1.2.
Side by side
| Claude 3.5 Haiku | Muse Spark 1.2 | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 29.2 | 50.3 |
| Released | 2024-10-22 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $4.25 |
| Results tracked | 49 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Claude 3.5 Haiku: 32.9 (#265), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| SciCode | 27.4% | 56.4% |
| WeirdML | 30.7% | 60.3% |
| LMArena Coding | 1286 | 1495 |
| DeepSWE | — | 54.9% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Muse Spark 1.2 leads
Claude 3.5 Haiku: 28.0 (#95), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| BALROG | 19.3% | — |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Claude 3.5 Haiku: 17.7 (#290), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| CritPt | 0% | 17.7% |
| LMArena Hard Prompts | 1251 | 1486 |
| DTBench | 56.7% | 94.7% |
| Epoch Capabilities Index | 127.15 | 154.87 |
| SimpleBench | — | 74.5% |
| NYT Connections (extended) | — | 79.2% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 48.4% |
| LiveBench | 43.5% | — |
Math Muse Spark 1.2 leads
Claude 3.5 Haiku: 14.7 (#300), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1244 | 1471 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| ProofBench | — | 43% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Muse Spark 1.2 leads
Claude 3.5 Haiku: 18.7 (#281), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1208 | 1480 |
| GPQA Diamond | 38.1% | — |
| SimpleQA Verified | — | 60.3% |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Muse Spark 1.2 leads
Claude 3.5 Haiku: 26.8 (#117), Muse Spark 1.2: 43.4 (#25)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1092 | 1305 |
| GeoBench | 34% | — |
Multilingual Muse Spark 1.2 leads
Claude 3.5 Haiku: 40.0 (#218), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1238 | 1478 |
| LMArena Chinese | 1229 | 1511 |
| LMArena French | 1264 | 1513 |
| LMArena Russian | 1253 | 1487 |
| LMArena Spanish | 1261 | 1498 |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
Instruction Following Muse Spark 1.2 leads
Claude 3.5 Haiku: 62.9 (#234), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1461 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Muse Spark 1.2 leads
Claude 3.5 Haiku: 38.3 (#200), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1261 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Claude 3.5 Haiku: 42.7 (#234), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Claude 3.5 Haiku | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1255 | 1482 |
| LMArena Creative Writing | 1233 | 1449 |
| EQ-Bench Creative Writing | 1146 | 1840 |
| LMArena Multi-Turn | 1265 | 1494 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Muse Spark 1.2 share?
21 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Muse Spark 1.2 has 31.