Model comparison
Claude Haiku 4.5 vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 39.5 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and Muse Spark 1.2 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 15.1.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 79.2% for Muse Spark 1.2.
- Both cost about the same: $1 input and $5 output per million tokens.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Haiku 4.5 | Muse Spark 1.2 | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 39.5 | 50.3 |
| Released | 2025-10-15 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $1 | $1.25 |
| Output $ / M tokens | $5 | $4.25 |
| Results tracked | 53 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Claude Haiku 4.5: 44.0 (#78), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1330 | 1533 |
| SciCode | 43.3% | 56.4% |
| WeirdML | 45.4% | 60.3% |
| LMArena Coding | 1453 | 1495 |
| DeepSWE | — | 54.9% |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| FrontierSWE | — | 12% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| APEX-Agents | — | 36.4% |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| GDP.pdf | — | 16% |
| Vending-Bench 2 | 458.89 | — |
Reasoning Muse Spark 1.2 leads
Claude Haiku 4.5: 15.1 (#320), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 14.3% | 79.2% |
| CritPt | 0% | 17.7% |
| LMArena Hard Prompts | 1420 | 1486 |
| DTBench | 73.6% | 94.7% |
| LMCA | 30.9% | 48.4% |
| Epoch Capabilities Index | 142.41 | 154.87 |
| ARC-AGI-2 | 4% | — |
| SimpleBench | — | 74.5% |
| ARC-AGI-1 | 47.7% | — |
| Chess Puzzles | 8% | — |
| ForecastBench | 61.4 | — |
Math Muse Spark 1.2 leads
Claude Haiku 4.5: 44.9 (#78), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1396 | 1471 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| ProofBench | — | 43% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Muse Spark 1.2 leads
Claude Haiku 4.5: 37.7 (#153), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 13.2% | 60.3% |
| LMArena Expert | 1442 | 1480 |
| GPQA Diamond | 71.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Muse Spark 1.2 leads
Claude Haiku 4.5: 26.8 (#118), Muse Spark 1.2: 43.4 (#25)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Muse Spark 1.2 leads
Claude Haiku 4.5: 49.9 (#129), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1377 | 1478 |
| LMArena Chinese | 1417 | 1511 |
| LMArena French | 1408 | 1513 |
| LMArena Russian | 1381 | 1487 |
| LMArena Spanish | 1420 | 1498 |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
Instruction Following Muse Spark 1.2 leads
Claude Haiku 4.5: 71.4 (#149), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1461 |
| IFEval | 80.1% | — |
Long Context Muse Spark 1.2 leads
Claude Haiku 4.5: 43.6 (#92), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1427 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Claude Haiku 4.5: 57.9 (#123), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1396 | 1482 |
| LMArena Creative Writing | 1372 | 1449 |
| LMArena Multi-Turn | 1409 | 1494 |
| EQ-Bench Creative Writing | — | 1840 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Muse Spark 1.2 share?
23 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Muse Spark 1.2 has 31.