Claude Haiku 4.5 vs Muse Spark 1.1
Muse Spark 1.1 leads Claude Haiku 4.5 on coding, 70.3 to 35.6 on the Vibe Coding Index, at about the same output price ($4.25 vs $5.00 per million). Updated October 22, 2026; 72 benchmarks have a result for both.
Claude Haiku 4.5 or Muse Spark 1.1: which to pick
Pick Muse Spark 1.1 for coding: it scores 70.3 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 3 benchmarks against 4.
Claude Haiku 4.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 72
- Claude Haiku 4.5 only
- 26
- Muse Spark 1.1 only
- 32
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Muse Spark 1.1
Muse Spark 1.1 scores 70.3 against 35.6.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Muse Spark 1.1
Muse Spark 1.1 leads, 33.7 against 16.9.
Same board, both measured
Agentic work
AA Agentic Index
Muse Spark 1.1
Muse Spark 1.1 leads, 25.8 against 8.0.
Same board, both measured
Reasoning
GPQA Diamond
Muse Spark 1.1
Muse Spark 1.1 leads, 91.2% against 72.2%.
Same board, both measured
Math
AIME
No call
Only Claude Haiku 4.5 has a AIME result, 82.7%.
Directional only
Knowledge
MMLU Pro
Muse Spark 1.1
Muse Spark 1.1 leads, 88.7% against 78.7%.
Same board, both measured
Web design
Design Arena: websites
Muse Spark 1.1
Muse Spark 1.1 leads, 1270 against 1122.
Same board, both measured
Long documents
Listed context window
Muse Spark 1.1
Muse Spark 1.1 takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Muse Spark 1.1
Claude Haiku 4.5 $0.0035, Muse Spark 1.1 $0.0034 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Muse Spark 1.1
Claude Haiku 4.5 $0.56, Muse Spark 1.1 $0.43.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Haiku 4.5 35.6 from 4 benchmarks, Muse Spark 1.1 70.3 from 3 benchmarks.
- Widest category
- Agentic work, 31.8 points apart on average over 6 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Claude Haiku 4.5 11.4% against Muse Spark 1.1 72.2%, 60.8 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 4.5 $5.00 against Muse Spark 1.1 $4.25 per million output tokens, 1.2x apart.
- Context window
- Claude Haiku 4.5 takes 200K tokens, Muse Spark 1.1 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Haiku 4.5 | Bars | Muse Spark 1.1 | Ties |
|---|---|---|---|---|
| Coding | 0 | 11 | 1 tie | |
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 6 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 10 | ||
| Web design | 0 | 8 | ||
| General | 0 | 26 | ||
| All shared boards | 0 | 71 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index011
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Multilingual | 64.7% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench coding | 48.1% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev | 1330 | 1542 | Muse Spark 1.1 |
| AA Coding Index | 43.9 | 71.3 | Muse Spark 1.1 |
| LiveCodeBench (Vals AI) | 41.2% | 85.9% | Muse Spark 1.1 |
| SWE-bench Verified (Vals AI) | 66.6% | 82.0% | Muse Spark 1.1 |
| Vibe Code Bench (Vals AI) | 11.4% | 72.2% | Muse Spark 1.1 |
| Code migration (Vals AI) | 7.5% | 31.1% | Muse Spark 1.1 |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| Terminal-Bench 2.1 (Vals AI) | 43.8% | 69.3% | Muse Spark 1.1 |
| SkillsBench (Vals AI) | Not measured | 59.2% | Only Muse Spark 1.1 measured |
| SciCode | Not measured | 58.8% | Only Muse Spark 1.1 measured |
| Terminal-Bench | 35.5% | Not measured | Only Claude Haiku 4.5 measured |
| WeirdML | 45.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: coding | 1454 | 1498 | Muse Spark 1.1 |
| LMArena Text: software and IT | 1439 | 1498 | Muse Spark 1.1 |
| LMArena WebDev: React | 1326 | 1532 | Muse Spark 1.1 |
| LMArena WebDev: HTML | 1318 | 1540 | Muse Spark 1.1 |
| LMArena WebDev: from an image | Not measured | 1540 | Only Muse Spark 1.1 measured |
| SWE Atlas: Codebase QnA | Not measured | 42.2% | Only Muse Spark 1.1 measured |
| SWE Atlas: Test Writing | Not measured | 41.5% | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.9 | 33.7 | Muse Spark 1.1 |
| Epoch Capabilities Index | 142.2 | 154.1 | Muse Spark 1.1 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| AA Agentic Index | 8.0 | 25.8 | Muse Spark 1.1 |
| Design Arena: agents building web apps | Not measured | 1207 | Only Muse Spark 1.1 measured |
| Design Arena: agents building full-stack apps | Not measured | 1199 | Only Muse Spark 1.1 measured |
| Design Arena: agents building mobile apps | Not measured | 1175 | Only Muse Spark 1.1 measured |
| Design Arena: agents building Android apps | Not measured | 1178 | Only Muse Spark 1.1 measured |
| Design Arena: agents building Godot games | Not measured | 1103 | Only Muse Spark 1.1 measured |
| Design Arena: agents building games | Not measured | 1183 | Only Muse Spark 1.1 measured |
| Design Arena: HTML slides | Not measured | 1145 | Only Muse Spark 1.1 measured |
| Design Arena: PowerPoint slides | Not measured | 1134 | Only Muse Spark 1.1 measured |
| Design Arena: spreadsheets | Not measured | 1021 | Only Muse Spark 1.1 measured |
| LiveBench research | 42.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench browser | 40.0% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench long agentic | 11.1% | Not measured | Only Claude Haiku 4.5 measured |
| Finance Agent (Vals AI) | 31.0% | 57.2% | Muse Spark 1.1 |
| Tax Agent Bench (Vals AI) | 5.9% | Not measured | Only Claude Haiku 4.5 measured |
| Legal Research Bench (Vals AI) | 10.6% | 38.0% | Muse Spark 1.1 |
| Excel Modeling Benchmark (Vals AI) | 22.7% | 56.4% | Muse Spark 1.1 |
| Time Horizon Index (Vals AI) | Not measured | 1.7% | Only Muse Spark 1.1 measured |
| APEX-Agents | Not measured | 31.8% | Only Muse Spark 1.1 measured |
| BALROG | 31.2% | Not measured | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | 45.5% | Not measured | Only Claude Haiku 4.5 measured |
| Vending-Bench 2 | $459 | $6,520 | Muse Spark 1.1 |
| Berkeley Function Calling Leaderboard (BFCL) | 68.7% | Not measured | Only Claude Haiku 4.5 measured |
| MCP Atlas | 40.2% | 88.1% | Muse Spark 1.1 |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | 91.2% | Muse Spark 1.1 |
| LiveBench reasoning | 61.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMMU Pro (Vals AI) | 46.1% | 86.6% | Muse Spark 1.1 |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.8% | Only Muse Spark 1.1 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 46.2% | Only Muse Spark 1.1 measured |
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI | 47.7% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only Claude Haiku 4.5 measured |
| Chess puzzles | 8.0% | 34.0% | Muse Spark 1.1 |
| LMArena Text: hard prompts | 1421 | 1485 | Muse Spark 1.1 |
| LMArena Text: expert | 1443 | 1478 | Muse Spark 1.1 |
| LMArena Text: hard prompts in English | 1435 | 1480 | Muse Spark 1.1 |
| LMArena Vision: diagrams | Not measured | 1305 | Only Muse Spark 1.1 measured |
| LMArena Vision: homework | Not measured | 1287 | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| AIME | 82.7% | Not measured | Only Claude Haiku 4.5 measured |
| MGSM (Vals AI) | 92.2% | Not measured | Only Claude Haiku 4.5 measured |
| OTIS Mock AIME | 66.7% | Not measured | Only Claude Haiku 4.5 measured |
| ProofBench | Not measured | 39.0% | Only Muse Spark 1.1 measured |
| MATH level 5 | 96.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: math | 1398 | 1482 | Muse Spark 1.1 |
| LMArena Text: mathematical work | 1430 | 1487 | Muse Spark 1.1 |
| MathArena | Not measured | 42.5% | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | 88.7% | Muse Spark 1.1 |
| LegalBench (Vals AI) | 81.2% | 85.0% | Muse Spark 1.1 |
| CaseLaw (Vals AI) | 56.5% | Not measured | Only Claude Haiku 4.5 measured |
| CorpFin (Vals AI) | 60.6% | 71.3% | Muse Spark 1.1 |
| TaxEval (Vals AI) | 67.5% | 79.7% | Muse Spark 1.1 |
| MortgageTax (Vals AI) | 62.2% | 66.1% | Muse Spark 1.1 |
| MedQA (Vals AI) | 79.6% | Not measured | Only Claude Haiku 4.5 measured |
| MedCode (Vals AI) | 32.7% | Not measured | Only Claude Haiku 4.5 measured |
| SimpleQA Verified | 13.2% | 57.8% | Muse Spark 1.1 |
| LMArena Text: science | 1406 | 1484 | Muse Spark 1.1 |
| LMArena Text: medicine and healthcare | 1394 | 1479 | Muse Spark 1.1 |
| LMArena Text: legal and government | 1400 | 1481 | Muse Spark 1.1 |
| LMArena Text: business and finance | 1400 | 1470 | Muse Spark 1.1 |
| PRBench Finance | Not measured | 55.0% | Only Muse Spark 1.1 measured |
| PRBench Legal | Not measured | 57.0% | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| Design Arena: websites | 1122 | 1270 | Muse Spark 1.1 |
| Design Arena: UI components | 1097 | 1287 | Muse Spark 1.1 |
| Design Arena: game dev | 1096 | 1269 | Muse Spark 1.1 |
| Design Arena: data viz | 1124 | 1267 | Muse Spark 1.1 |
| Design Arena: 3D | 1071 | 1259 | Muse Spark 1.1 |
| Design Arena: all code categories | 1114 | 1276 | Muse Spark 1.1 |
| Design Arena: SVG | 1025 | 1234 | Muse Spark 1.1 |
| Design Arena: ASCII art | 1140 | 1269 | Muse Spark 1.1 |
| LiveBench design | 59.9% | Not measured | Only Claude Haiku 4.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index026
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| LiveBench data analysis | 59.3% | Not measured | Only Claude Haiku 4.5 measured |
| Public Benefits Bench (Vals AI) | 54.3% | 61.3% | Muse Spark 1.1 |
| SAGE (Vals AI) | 31.8% | 45.6% | Muse Spark 1.1 |
| MedScribe (Vals AI) | 85.2% | 88.9% | Muse Spark 1.1 |
| Vals Multimodal Index | 42.9% | 66.7% | Muse Spark 1.1 |
| Long context reasoning (AA-LCR) | Not measured | 77.7% | Only Muse Spark 1.1 measured |
| DTBench | 73.6% | 94.4% | Muse Spark 1.1 |
| LMCA | 30.9% | 49.9% | Muse Spark 1.1 |
| Surface Evolver Bench | Not measured | 52.5% | Only Muse Spark 1.1 measured |
| ExploitBench | 13.7% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text | 1397 | 1478 | Muse Spark 1.1 |
| LMArena Text: instruction following | 1414 | 1457 | Muse Spark 1.1 |
| LMArena Text: creative writing | 1371 | 1435 | Muse Spark 1.1 |
| LMArena Vision | Not measured | 1293 | Only Muse Spark 1.1 measured |
| LMArena Text: English | 1414 | 1478 | Muse Spark 1.1 |
| LMArena Text: non-English | 1377 | 1471 | Muse Spark 1.1 |
| LMArena Text: Chinese | 1418 | 1515 | Muse Spark 1.1 |
| LMArena Text: German | 1374 | 1469 | Muse Spark 1.1 |
| LMArena Text: Japanese | 1338 | 1450 | Muse Spark 1.1 |
| LMArena Text: Korean | 1346 | 1459 | Muse Spark 1.1 |
| LMArena Text: French | 1411 | 1492 | Muse Spark 1.1 |
| LMArena Text: Spanish | 1421 | 1464 | Muse Spark 1.1 |
| LMArena Text: Russian | 1381 | 1482 | Muse Spark 1.1 |
| LMArena Text: Polish | 1343 | 1499 | Muse Spark 1.1 |
| LMArena Text: multi-turn | 1409 | 1484 | Muse Spark 1.1 |
| LMArena Text: longer queries | 1427 | 1462 | Muse Spark 1.1 |
| LMArena Text: writing and language | 1386 | 1448 | Muse Spark 1.1 |
| LMArena Text: entertainment and media | 1369 | 1438 | Muse Spark 1.1 |
| LMArena Vision: English | Not measured | 1292 | Only Muse Spark 1.1 measured |
| LMArena Vision: Chinese | Not measured | 1348 | Only Muse Spark 1.1 measured |
| LMArena Vision: reading text | Not measured | 1301 | Only Muse Spark 1.1 measured |
| LMArena Vision: humor | Not measured | 1288 | Only Muse Spark 1.1 measured |
| LMArena Vision: creative writing | Not measured | 1253 | Only Muse Spark 1.1 measured |
| LMArena Document | 1420 | 1465 | Muse Spark 1.1 |
| MultiChallenge | 50.5% | 75.3% | Muse Spark 1.1 |
| EQ-Bench 4 | 1064 | 1260 | Muse Spark 1.1 |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 4.5 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Muse Spark 1.1 costs less
Repository review
50K input + 3K output tokens
Claude Haiku 4.5 costs less
Agent loop
200K input + 10K output tokens
Claude Haiku 4.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Haiku 4.5 | Meta Muse Spark 1.1 |
|---|---|---|
| Maker | Anthropic | Meta |
| Weights | No public weights listed | No public weights listed |
| Released | October 15, 2025 | July 16, 2026 |
| Context window | 200K | 1.05M |
| Input $/Mtok | $1.00 | $1.25 |
| Output $/Mtok | $5.00 | $4.25 |
| Coding index | 35.6 | 70.3 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | $0.56 | $0.43 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 4.5 better than Muse Spark 1.1 for coding?
Pick Muse Spark 1.1 for coding: it scores 70.3 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 3 benchmarks against 4. Claude Haiku 4.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, Claude Haiku 4.5 or Muse Spark 1.1?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Muse Spark 1.1 costs $1.25 and $4.25. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Muse Spark 1.1 $0.43.
Which has the bigger context window, Claude Haiku 4.5 or Muse Spark 1.1?
Muse Spark 1.1, with 1.05M tokens against 200K.
How many benchmarks is the Claude Haiku 4.5 vs Muse Spark 1.1 comparison based on?
72 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and Muse Spark 1.1's on 3. Where only one model has a result, the page says so instead of naming a winner.