Muse Spark 1.1 vs Muse Spark 1.3
Full profiles: Muse Spark 1.1 (Meta) and Muse Spark 1.3 (Meta): every benchmark, price and rank.
Updated · Data from 8 sources
As of 24 Oct 2026, Muse Spark 1.1 and Muse Spark 1.3 (max) are neck and neck on quality (62.5 vs 67.1, inside the ±7.1 margin of error) and cost about the same, so speed decides it: Muse Spark 1.1 streams 1.7× faster. Pick Muse Spark 1.1 for coding (66 vs 65); pick Muse Spark 1.3 for agents & tools (66 vs 52).
Muse Spark 1.1 benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Muse Spark 1.1 | 66 vs 65 category score; Arena WebDev 1543 vs 1657 | Medium |
| Agents & tool use | Muse Spark 1.3 | 66 vs 52 category score; APEX-Agents 47.6% vs 31.8% | High |
| Maths | Muse Spark 1.3 | 63 vs 61 category score; Arena Maths 1510 vs 1493 | Medium |
| Reasoning | Muse Spark 1.3 | 77 vs 68 category score; Arena Hard Prompts 1517 vs 1510 | High |
| Knowledge | Muse Spark 1.3 | 73 vs 69 category score | Medium |
| Images and other media | Muse Spark 1.3 | 66 vs 64 category score; Arena Vision 1308 vs 1293 | Medium |
| Chat quality (human preference) | Muse Spark 1.3 | 69 vs 65 on Arena votes | Medium |
| Lowest cost | Either | $2.00 vs $2.00 per 1M blended; agentic coding session $0.092 vs $0.092 | – |
| Fastest first answer | Muse Spark 1.1 | 1.6 s (Muse Spark 1.1) vs 90.1 s (Muse Spark 1.3 (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Muse Spark 1.1 and Muse Spark 1.3 (max) are neck and neck on quality (62.5 vs 67.1, within the ±7.1 margin).
- Muse Spark 1.1 is stronger in coding, instruction following.
- Muse Spark 1.3 (max) is stronger in agents & tools, human preference, knowledge, maths, multimodal, reasoning, composite, long context.
- They cost about the same ($2.00 per 1M blended).
- Muse Spark 1.1 streams 1.7× faster (200 vs 116 tokens per second).
At a glance
| Spec | Muse Spark 1.1 | Muse Spark 1.3 |
|---|---|---|
| Developer | Meta | Meta |
| Released | 9 Jul 2026 | 2 Sept 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Muse Spark 1.1 | Muse Spark 1.3 (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $1.25 / $4.25 / $0.150 | $1.25 / $4.25 / $0.150 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Muse Spark 1.1 | Muse Spark 1.3 (max) | Leader |
|---|---|---|---|
| Reasoning | 67.9 | 77.4 | Muse Spark 1.3 |
| Coding | 66.3 | 64.5 | Muse Spark 1.1 |
| Agents & tools | 51.5 | 65.6 | Muse Spark 1.3 |
| Maths | 61.3 | 63.4 | Muse Spark 1.3 |
| Knowledge | 69.2 | 72.8 | Muse Spark 1.3 |
| Instruction following | 71.5 | – | not comparable |
| Human preference | 65.3 | 69.1 | Muse Spark 1.3 |
| Multimodal | 63.6 | 65.7 | Muse Spark 1.3 |
| Long context | – | 66.6 | not comparable |
| Composite | – | 83.3 | not comparable |
Where sources disagree
Across the 14 benchmarks both have, Muse Spark 1.1 leads 2, Muse Spark 1.3 leads 11 and 1 is a tie. Every overall index that rates both puts Muse Spark 1.3 ahead.
| Overall index | Muse Spark 1.1 | Muse Spark 1.3 (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 62.5 | 67.1 | neck and neck |
| AA Intelligence Index v4.3.2 | 33.7† | 48.1 | Muse Spark 1.3 |
| Arena Text | 1490 | 1496 | Muse Spark 1.3 |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | Muse Spark 1.1 | Muse Spark 1.3 (max) |
|---|---|---|
| Blended price per 1M tokens | $2.00 | $2.00 |
| Input / output per 1M | $1.25 / $4.25 | $1.25 / $4.25 |
| Cached input per 1M | $0.150 | $0.150 |
| Price per task: chat reply | $0.0018 | $0.0018 |
| Price per task: summarize a 30-page report | $0.018 | $0.018 |
| Price per task: code edit | $0.014 | $0.014 |
| Price per task: agentic coding session | $0.092 | $0.092 |
| Price per task: structured extraction | $0.0034 | $0.0034 |
| Cost to run a full benchmark suite | – | $1.60 |
| Output speed | 200 tok/s | 116 tok/s |
| Time to first answer | 1.6 s | 90.1 s |
| Time to a complete answer | – | 94.4 s |
Each model is compared at its best-ranked reasoning-effort setting. Muse Spark 1.1 scores 62.5 and takes 2 s to its first answer token; Muse Spark 1.1 (xhigh) scores 61.6 in 18 s. Muse Spark 1.3 (max) scores 67.1 and takes 90 s to its first answer token; Muse Spark 1.3 (xhigh) scores 64.9 in 30 s, Muse Spark 1.3 scores 59.8 in 3 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
122 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Muse Spark 1.1 | Muse Spark 1.3 (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 62.5 | 67.1 |
| Agents & tools score | BenchLeader | 51.5 | 65.6 |
| Coding score | BenchLeader | 66.3 | 64.5 |
| Human preference score | BenchLeader | 65.3 | 69.1 |
| Instruction following score | BenchLeader | 71.5 | – |
| Knowledge score | BenchLeader | 69.2 | 72.8 |
| Maths score | BenchLeader | 61.3 | 63.4 |
| Multimodal score | BenchLeader | 63.6 | 65.7 |
| Reasoning score | BenchLeader | 67.9 | 77.4 |
| Composite score | BenchLeader | – | 83.3 |
| Long context score | BenchLeader | – | 66.6 |
| Blended price $/M | BenchLeader | $2.00 | $2.00 |
| Output speed | BenchLeader | 200 tok/s | 116 tok/s |
| Time to first answer | BenchLeader | 1.6 s | 90.1 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | 1510 | 1517 |
| LiveBench 2.0 Reasoning | LiveBench | – | 89.7%† |
| LiveBench 1.0 Reasoning | LiveBench | 87.7%† | 89.7%† |
| GPQA Diamond (AA) | Artificial Analysis | 89.8%† | 93.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 46.2%† | 48.7% |
| GPQA Diamond (Vals) | Vals AI | 91.2%† | – |
| CritPt | Artificial Analysis | 15.1%† | 24.9% |
| MysteryMechanism | Vals AI | – | 36.0% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 34.0%† | 37.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 25.0% |
| LMCA | Epoch AI Benchmarking Hub | 49.9%† | 53.9%† |
| DTBench | Epoch AI Benchmarking Hub | 94.4%† | 96.5%† |
| BTF-3 | Epoch AI Benchmarking Hub | – | 14.1%† |
| Coding | |||
| SciCode | SciCode | 58.8% | 58.8% |
| Arena Coding | Arena (LMArena) | 1533 | 1536 |
| Arena WebDev | Arena (LMArena) | 1543 | 1657 |
| LiveBench 2.0 Coding | LiveBench | – | 90.2%† |
| LiveBench 1.0 Coding | LiveBench | 77.2%† | 81.1%† |
| LiveCodeBench | Vals AI | 85.9%† | – |
| IOI | Vals AI | – | 56.6% |
| SWE-bench (Vals) | Vals AI | 82.0%† | – |
| SWE-Bench Pro | Scale AI SEAL | 61.5% | – |
| Code Migration | Vals AI | 31.1%† | 47.4% |
| ProgramBench | Vals AI | 0.0%† | 2.5% |
| SWE-bench Multimodal | Vals AI | – | 43.1% |
Show all 122 benchmarks
| Metric | Publisher | Muse Spark 1.1 | Muse Spark 1.3 (max) |
|---|---|---|---|
| Coding | |||
| Vibe Code Bench 1-100 | Vals AI | – | 20.5% |
| Vibe Code Bench v1.1 | Vals AI | 72.2%† | 85.9% |
| SWE-Bench Pro (private) | Scale AI SEAL | 61.5% | – |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 42.2%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 41.5%† | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 52.5%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 53.3% | – |
| CursorBench | Cursor | – | 41.6% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 1688.3† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 25.8% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 6.1%† | 33.3% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 77.9%† | 84.3% |
| Startrise Frontend | Startrise | – | 74.7%† |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 40.6% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 14.6%† |
| APEX-Agents | Mercor | 31.8% | 47.6% |
| Arena Agent | Arena (LMArena) | -6.6 | 3.4 |
| LiveBench Long Agentic | LiveBench | – | 40.4%† |
| LiveBench Browser | LiveBench | – | 80.0%† |
| LiveBench Agentic Coding | LiveBench | 58.5%† | 64.1%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | 69.3%† | 79.0% |
| MCP Atlas | Scale AI SEAL | 88.1% | – |
| HiL-Bench | Scale AI SEAL | – | 66.9%† |
| τ³-bench Banking | τ²-bench | 40.5%† | – |
| τ³-Banking (AA) | Artificial Analysis | 31.8%† | 50.5% |
| ITBench SRE (AA) | Artificial Analysis | – | 33.2% |
| Analyst Agent (AA) | Artificial Analysis | – | 37.5% |
| CUA-bench | Vals AI | – | 5.8% |
| CyberBench | Vals AI | – | 72.7% |
| Finance Agent v2 | Vals AI | 57.2%† | 60.0% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 20.0%† | 23.8% |
| Legal Research Bench | Vals AI | 38.0%† | 55.3% |
| SkillsBench | Vals AI | 59.2%† | – |
| SREBench | Vals AI | – | 3.8% |
| Tax Agent Bench | Vals AI | – | 42.4% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 24.8% |
| Terminal-Bench Science | Vals AI | – | 10.0% |
| Time Horizon Index: KSP | Vals AI | 1.7%† | – |
| GBAEval | Epoch AI Benchmarking Hub | 7.9% | – |
| Vending-Bench 2 | Andon Labs | 6520.5 | – |
| AutomationBench | Artificial Analysis | 38.9%† | 57.9% |
| GDP.pdf (AA) | Artificial Analysis | 14.4%† | 26.6% |
| Harvey LAB-AA v1.1 | Harvey | – | 8.9% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1581 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 10.9% |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 74.0% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 46.3% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 99.2%† |
| ProofBench | Vals AI | 39.0% | 58.0% |
| LiveBench Mathematics | LiveBench | 87.1%† | 96.0%† |
| Arena Maths | Arena (LMArena) | 1493 | 1510 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 57.8% | – |
| LiveBench 2.0 Data Analysis | LiveBench | – | 79.6%† |
| LiveBench Research | LiveBench | – | 68.6%† |
| LiveBench 1.0 Data Analysis | LiveBench | 72.5%† | 79.6%† |
| AA-Omniscience | Artificial Analysis | 28.1† | 25 |
| MMLU-Pro | Vals AI | 88.7%† | – |
| LegalBench | Vals AI | 85.0%† | – |
| CorpFin | Vals AI | 71.3%† | – |
| TaxEval | Vals AI | 79.7%† | – |
| PRBench Finance | Scale AI SEAL | 55.0% | 59.5%† |
| PRBench Legal | Scale AI SEAL | 57.0% | 61.6%† |
| MultiNRC | Scale AI SEAL | 65.6% | – |
| Excel Modeling Benchmark | Vals AI | 56.4%† | 67.4% |
| MedScribe | Vals AI | 88.9%† | – |
| Public Benefits Bench v1.1 | Vals AI | 61.3%† | – |
| DrugDiscoveryBench | Scale AI SEAL | – | 62.2%† |
| GDP.pdf | Epoch AI Benchmarking Hub | 15.0% | 27.6%† |
| AA-Omniscience: accuracy | Artificial Analysis | 52.0%† | 43.6% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 50.0%† | 67.1% |
| Instruction following | |||
| LiveBench Language | LiveBench | 74.3%† | 82.8%† |
| LiveBench Instruction Following | LiveBench | 69.6%† | 78.0%† |
| MultiChallenge | Scale AI SEAL | 75.3% | – |
| Arena Instruction Following | Arena (LMArena) | 1472 | 1485 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1490 | 1496 |
| EQ-Bench 4 | EQ-Bench | 1260 | – |
| Arena Creative Writing | Arena (LMArena) | 1443 | 1463 |
| Arena Multi-turn | Arena (LMArena) | 1496 | 1494 |
| Arena Longer Queries | Arena (LMArena) | 1480 | 1497 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1293 | 1308 |
| LiveBench Design | LiveBench | – | 74.8%† |
| MMMU-Pro | Artificial Analysis | – | 82.0%† |
| MMMU-Pro (Vals) | Vals AI | 86.6%† | – |
| MortgageTax | Vals AI | 66.1%† | – |
| SAGE | Vals AI | 45.6%† | – |
| VTB | Scale AI SEAL | 44.8% | – |
| AA-3D | Artificial Analysis | – | 1037 |
| Long context | |||
| AA-LCR | Artificial Analysis | 77.7%† | 83.0% |
| Arena Document | Arena (LMArena) | 1480 | 1468 |
| MLCR | Artificial Analysis | 7.2%† | 13.9% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 154.1 | 157.2† |
| LiveBench 2.0 | LiveBench | – | 74.8%† |
| LiveBench 1.0 | LiveBench | 75.3%† | 81.6%† |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 33.7† | 48.1 |
| Vals RSI Index | Vals AI | – | 19.6% |
| Vals Multimodal Index | Vals AI | 66.7%† | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 12.4% | – |
Data as of 2026-10-24. Best configuration of each model; every score links to its source on the model pages.
What changed
- Muse Spark 1.3 (max): 3 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index, SWE-bench Multimodal); 1 score revision.
- Muse Spark 1.1: BenchLeader Index 63.1 → 62.5.
- Muse Spark 1.3 (max): 1 score revision.
- Muse Spark 1.3 (max): 1 score revision.
- Muse Spark 1.3 (max): 2 new results (ProgramBench, SREBench); 1 score revision.
- Muse Spark 1.1: 1 score revision.
- Muse Spark 1.3 (max): 2 new results (APEX-Agents, FrontierSWE); 1 score revision.
- Muse Spark 1.3 (max): BenchLeader Index 68.0 → 67.5.
- Muse Spark 1.1: 1 new result (PRBench Legal).
- Muse Spark 1.3 (max): 1 new result (Analyst Agent (AA)); 1 score revision.
Related comparisons
- Muse Spark 1.1 vs Claude Opus 5.5
- Muse Spark 1.1 vs Gemini 4 Argon
- Muse Spark 1.1 vs Muse Wonder Full
- Muse Spark 1.3 vs Claude Opus 5.5
- Muse Spark 1.3 vs Gemini 4 Argon
- Muse Spark 1.3 vs Muse Wonder Full
- Muse Spark 1.3 vs Claude Fable 5.1
- Muse Spark vs Muse Spark 1.3
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Muse Spark 1.1 vs Muse Spark 1.3: questions
- Is Muse Spark 1.1 better than Muse Spark 1.3?
- Muse Spark 1.1 and Muse Spark 1.3 (max) are neck and neck on quality (62.5 vs 67.1, within the ±7.1 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-24, so check the category scores for your use.
- Which is cheaper, Muse Spark 1.1 or Muse Spark 1.3, and will that change?
- They cost the same: $2.00 per million tokens blended. No price change has been announced for either.
- Is Muse Spark 1.1 better than Muse Spark 1.3 for coding?
- Muse Spark 1.1 scores higher in coding (66 vs 65 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1543 for Muse Spark 1.1 against 1657 for Muse Spark 1.3.
- Is Muse Spark 1.1 better than Muse Spark 1.3 for agents and tool use?
- Muse Spark 1.3 scores higher in agentic tasks (66 vs 52 on the category index, where 50 is average). On APEX-Agents, the top shared agents & tools benchmark, it is 31.8% for Muse Spark 1.1 against 47.6% for Muse Spark 1.3.
- Which is better for long documents?
- Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Muse Spark 1.1 answers first: 1.6 s against 90.1 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Which is faster, Muse Spark 1.1 or Muse Spark 1.3?
- Muse Spark 1.1 streams faster: 200 against 116 output tokens per second.
- Do independent benchmarks agree on Muse Spark 1.1 vs Muse Spark 1.3?
- Across the 14 benchmarks both have, Muse Spark 1.1 leads 2, Muse Spark 1.3 leads 11 and 1 is a tie. Every overall index that rates both puts Muse Spark 1.3 ahead.
- When was Muse Spark 1.3 released?
- Muse Spark 1.3 was released on 2 Sept 2026.