Claude Sonnet 4.6 vs Muse Spark 1.3
Full profiles: Claude Sonnet 4.6 (Anthropic) and Muse Spark 1.3 (Meta): every benchmark, price and rank.
Updated · Data from 10 sources
As of 14 Nov 2026, Muse Spark 1.3 is ahead of Claude Sonnet 4.6 on quality (61.5 vs 58.3 on the BenchLeader Index), and Muse Spark 1.3 is 3.0× cheaper at $2.00 vs $6.00 per 1M tokens blended. Choose Claude Sonnet 4.6 for reasoning (64 vs 60) and knowledge (60 vs 57) and fast first answers (0.7 s vs 28.8 s); choose Muse Spark 1.3 for agents & tools (65 vs 51), human preference (69 vs 61), and coding (60 vs 55), where it also streams 3×+ faster.
Key facts (as of 14 Nov 2026)
- Claude Sonnet 4.6 scores 58.3 on the BenchLeader Index and Muse Spark 1.3 scores 61.5 (BenchLeader, 14 Nov 2026).
- Claude Sonnet 4.6 costs $6.00 per 1M tokens blended (list price, 14 Nov 2026).
- Muse Spark 1.3 costs $2.00 per 1M tokens blended (list price, 14 Nov 2026).
- Muse Spark 1.3 streams 3×+ faster than Claude Sonnet 4.6 (Artificial Analysis, 7-day median, 14 Nov 2026).
- Of the 23 benchmarks both models have, Muse Spark 1.3 leads 22 (BenchLeader, 14 Nov 2026).
- On Arena WebDev, Claude Sonnet 4.6 is rated 1522 and Muse Spark 1.3 1655 (LMArena, as published by 14 Nov 2026).
Claude Sonnet 4.6 benchmarks 
Muse Spark 1.3 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 1.3 | 60 vs 55 category score; Arena WebDev 1655 vs 1522 | Medium |
| Agents & tool use | Muse Spark 1.3 | 65 vs 51 category score; Terminal-Bench 2.1 (Vals) 79.0% vs 57.3% | High |
| Maths | Either | 63 vs 63 category score; Arena Maths 1461 vs 1506 | Either |
| Reasoning | Claude Sonnet 4.6 | 64 vs 60 category score; Arena Hard Prompts 1503 vs 1517 | Medium |
| Knowledge | Claude Sonnet 4.6 | 60 vs 57 category score; Excel Modeling Benchmark 60.1% vs 67.4% | Medium |
| Images and other media | Muse Spark 1.3 | 66 vs 62 category score; Arena Vision 1310 vs 1283 | Medium |
| Chat quality (human preference) | Muse Spark 1.3 | 69 vs 61 on Arena votes | High |
| Lowest cost | Muse Spark 1.3 | $2.00 vs $6.00 per 1M blended; agentic coding session $0.092 vs $0.240 | – |
| Fastest first answer | Claude Sonnet 4.6 | 0.7 s (Claude Sonnet 4.6) vs 28.8 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 1.3 (max) leads on quality: 61.5 vs 58.3.
- Claude Sonnet 4.6 is stronger in knowledge, maths, reasoning.
- Muse Spark 1.3 (max) is stronger in agents & tools, coding, human preference, multimodal.
- Muse Spark 1.3 (max) is 3.0× cheaper ($2.00 vs $6.00 per 1M blended).
- Muse Spark 1.3 (max) streams 3.0× faster (132 vs 44 tokens per second).
At a glance
| Spec | Claude Sonnet 4.6 | Muse Spark 1.3 |
|---|---|---|
| Developer | Anthropic | Meta |
| Released | 17 Feb 2026 | 2 Sep 2026 |
| Context window (tokens) | 1,000,000 | 1,048,576 |
| Compared at | Claude Sonnet 4.6 | Muse Spark 1.3 (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $3.00 / $15.00 / $0.300 | $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 | Claude Sonnet 4.6 | Muse Spark 1.3 (max) | Leader |
|---|---|---|---|
| Reasoning | 63.9 | 59.6 | Claude Sonnet 4.6 |
| Coding | 55.2 | 60.4 | Muse Spark 1.3 |
| Agents & tools | 51.3 | 65.0 | Muse Spark 1.3 |
| Maths | 63.1 | 62.7 | level |
| Knowledge | 59.8 | 57.0 | Claude Sonnet 4.6 |
| Human preference | 60.5 | 69.0 | Muse Spark 1.3 |
| Multimodal | 62.4 | 65.9 | Muse Spark 1.3 |
| Long context | – | 66.2 | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Instruction following, Long context.
Model, click to add or removeIndex
Where sources disagree
Across the 23 benchmarks both have, Claude Sonnet 4.6 leads 1, Muse Spark 1.3 leads 22. Every overall index that rates both puts Muse Spark 1.3 ahead.
| Overall index | Claude Sonnet 4.6 | Muse Spark 1.3 (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 58.3 | 61.5 | Muse Spark 1.3 |
| Arena Text | 1472 | 1497 | 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Claude Sonnet 4.6 | Muse Spark 1.3 (max) |
|---|---|---|
| Blended price per 1M tokens | $6.00 | $2.00 |
| Input / output per 1M | $3.00 / $15.00 | $1.25 / $4.25 |
| Cached input per 1M | $0.300 | $0.150 |
| Price per task: chat reply | $0.0057 | $0.0018 |
| Price per task: summarize a 30-page report | $0.045 | $0.018 |
| Price per task: code edit | $0.041 | $0.014 |
| Price per task: agentic coding session | $0.240 | $0.092 |
| Price per task: structured extraction | $0.0090 | $0.0034 |
| Agentic coding session, input mostly cached | $0.118 | $0.043 |
| Cost per benchmark task (AA Index) | – | $2.39 |
| Output tokens per task (AA Index) | – | 91k |
| Of which reasoning | – | 55k |
| Time per task (AA Index) | – | 12 min |
| Output speed | 44 tok/s | 132 tok/s |
| Time to first answer | 0.7 s | 28.8 s |
| Time to a complete answer | – | 67.1 s |
Each model is compared at its best-ranked reasoning-effort setting. Claude Sonnet 4.6 scores 58.3 and takes 1 s to its first answer token; Claude Sonnet 4.6 (max) scores 54.0 in 123 s, Claude Sonnet 4.6 (high) scores 50.3 in 1 s. Muse Spark 1.3 (max) scores 61.5 and takes 29 s to its first answer token; Muse Spark 1.3 scores 60.3 in 3 s, Muse Spark 1.3 (xhigh) scores 58.0 in 17 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
147 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 | Claude Sonnet 4.6 | Muse Spark 1.3 (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 58.3 | 61.5 |
| Agents & tools score | BenchLeader | 51.3 | 65.0 |
| Coding score | BenchLeader | 55.2 | 60.4 |
| Human preference score | BenchLeader | 60.5 | 69.0 |
| Knowledge score | BenchLeader | 59.8 | 57.0 |
| Maths score | BenchLeader | 63.1 | 62.7 |
| Multimodal score | BenchLeader | 62.4 | 65.9 |
| Reasoning score | BenchLeader | 63.9 | 59.6 |
| Long context score | BenchLeader | – | 66.2 |
| Blended price $/M | BenchLeader | $6.00 | $2.00 |
| Output speed | BenchLeader | 44 tok/s | 132 tok/s |
| Time to first answer | BenchLeader | 0.7 s | 28.8 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 87.4% | – |
| SimpleBench | SimpleBench | – | 81.8%† |
| Arena Hard Prompts | Arena (LMArena) | 1503 | 1517 |
| LiveBench 2.0 Reasoning | LiveBench | – | 89.7%† |
| LiveBench 1.0 Reasoning | LiveBench | 84.8%† | 89.7%† |
| GPQA Diamond (AA) | Artificial Analysis | 87.5%† | 93.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 33.6%† | 48.7% |
| HLE-Diamond (AA) | Artificial Analysis | – | 33.7% |
| GPQA Diamond (Vals) | Vals AI | 85.6% | – |
| ARC-AGI-1 | ARC Prize | 86.0%† | – |
| ARC-AGI-2 | ARC Prize | 58.3%† | – |
| CritPt | Artificial Analysis | 3.1%† | 24.9% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 48.0% |
| MysteryMechanism | Vals AI | – | 36.0% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 23.0%† | 37.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 14.0% | 25.0% |
| LMCA | Epoch AI Benchmarking Hub | 46.5%† | 53.9%† |
| DTBench | Epoch AI Benchmarking Hub | 89.9%† | 96.5%† |
| ForecastBench | ForecastBench | 64.0% | 65.5% |
| BTF-3 | Epoch AI Benchmarking Hub | – | 14.1%† |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 75.2% | – |
| SciCode | SciCode | 46.8%† | 58.8% |
| WeirdML | WeirdML | 66.1%† | – |
| FrontierCode | Cognition | 24.3% | – |
| Arena Coding | Arena (LMArena) | 1528 | 1534 |
Show all 147 benchmarks
| Metric | Publisher | Claude Sonnet 4.6 | Muse Spark 1.3 (max) |
|---|---|---|---|
| Coding | |||
| Arena WebDev | Arena (LMArena) | 1522 | 1655 |
| LiveBench 2.0 Coding | LiveBench | – | 84.4%† |
| LiveBench 1.0 Coding | LiveBench | 79.3%† | 81.1%† |
| SciCode (AA) | Artificial Analysis | 50.1%† | 58.8% |
| LiveCodeBench | Vals AI | 82.1% | – |
| IOI | Vals AI | – | 56.6% |
| SWE-bench (Vals) | Vals AI | 77.4% | – |
| Code Migration | Vals AI | 39.9% | 47.4% |
| ProgramBench | Vals AI | 0.5% | 2.5% |
| SWE-bench Multimodal | Vals AI | – | 43.1% |
| Vibe Code Bench 1-100 | Vals AI | – | 20.5% |
| Vibe Code Bench v1.1 | Vals AI | 51.5% | 85.9% |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 31.2% | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 32.2% | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 31.8% | – |
| MirrorCode | Epoch AI Benchmarking Hub | – | 54.4% |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 29.9%† | – |
| CursorBench | Cursor | – | 41.6% |
| ALE-Bench | Epoch AI Benchmarking Hub | 1327.3† | 1688.3† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 25.8% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 3.0%† | 33.3% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 71.2%† | 84.3% |
| Startrise Frontend | Startrise | – | 74.7%† |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 57.6† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 68.6† |
| Design Arena Website | Design Arena | 1277 | 1353 |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 40.6% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 23.1% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 53.4% | 14.8%† |
| OSWorld-Verified 2.0 | OSWorld | 8.3%† | – |
| APEX-Agents | Mercor | 43.0%† | 47.6% |
| Arena Agent | Arena (LMArena) | – | 2.2 |
| LiveBench Long Agentic | LiveBench | – | 47.9%† |
| LiveBench Browser | LiveBench | – | 30.9%† |
| LiveBench Agentic Coding | LiveBench | 42.6%† | 64.1%† |
| Terminal-Bench Hard | Artificial Analysis | 53.0%† | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 75.7%† | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | 57.3% | 79.0% |
| MCP Atlas | Scale AI SEAL | 69.5% | – |
| HiL-Bench | Scale AI SEAL | – | 66.9%† |
| τ³-Banking (AA) | Artificial Analysis | 34.4%† | 50.5% |
| ITBench SRE (AA) | Artificial Analysis | 39.8%† | 33.2% |
| Analyst Agent (AA) | Artificial Analysis | 20.0%† | 37.5% |
| APEX-Agents (AA) | Artificial Analysis | 28.0%† | – |
| CUA-bench | Vals AI | – | 5.8% |
| CyberBench | Vals AI | – | 72.7% |
| Finance Agent v2 | Vals AI | 51.0% | 60.0% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 5.0% | 23.8% |
| Legal Research Bench | Vals AI | 38.5% | 55.3% |
| SkillsBench | Vals AI | 49.0% | – |
| SREBench | Vals AI | – | 3.8% |
| Tax Agent Bench | Vals AI | 25.8% | 42.4% |
| Terminal-Bench 2.0 (Vals) | Vals AI | 59.5% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 24.8% |
| Terminal-Bench Science | Vals AI | – | 10.0% |
| Arena Search | Arena (LMArena) | 1201 | – |
| DeepResearch Bench | DeepResearch Bench | 54.9%† | – |
| ExploitBench | Epoch AI Benchmarking Hub | 23.6% | – |
| GBAEval | Epoch AI Benchmarking Hub | 48.8% | – |
| Vending-Bench 2 | Andon Labs | 7204.1 | – |
| AutomationBench | Artificial Analysis | 20.1%† | 57.9% |
| GDP.pdf (AA) | Artificial Analysis | 15.8%† | 26.6% |
| Harvey LAB-AA v1.1 | Harvey | – | 8.9% |
| AA-Briefcase v1.1 | Artificial Analysis | 1062† | 1581 |
| Design Arena Agentic | Design Arena | 1181 | 1278 |
| 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 | 85.8% | 99.2%† |
| ProofBench | Vals AI | 45.0%† | 58.0% |
| LiveBench Mathematics | LiveBench | 87.0%† | 96.0%† |
| AIME (Vals) | Vals AI | 92.3% | – |
| Arena Maths | Arena (LMArena) | 1461 | 1506 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 32.8%† | – |
| LiveBench 2.0 Data Analysis | LiveBench | – | 79.6%† |
| LiveBench Research | LiveBench | – | 82.5%† |
| LiveBench 1.0 Data Analysis | LiveBench | 78.0%† | 79.6%† |
| AA-Omniscience v1.1 | Artificial Analysis | – | 22.4 |
| MMLU-Pro | Vals AI | 87.3% | – |
| LegalBench | Vals AI | 82.1% | – |
| CorpFin | Vals AI | 65.3% | – |
| TaxEval | Vals AI | 77.1% | – |
| MedQA | Vals AI | 92.1% | – |
| PRBench Finance | Scale AI SEAL | – | 59.5%† |
| PRBench Legal | Scale AI SEAL | – | 61.6%† |
| CaseLaw v2 | Vals AI | 64.0% | – |
| Excel Modeling Benchmark | Vals AI | 60.1% | 67.4% |
| Public Benefits Bench v1.1 | Vals AI | 62.5% | – |
| DrugDiscoveryBench | Scale AI SEAL | 31.3%† | 62.2%† |
| GDP.pdf | Epoch AI Benchmarking Hub | 18.0%† | 27.6%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 38.0% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 74.8% |
| Global-MMLU-Lite (AA) | Artificial Analysis | 90.5%† | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 76.1%† | 82.8%† |
| LiveBench Instruction Following | LiveBench | 63.2%† | 78.0%† |
| IFBench | Artificial Analysis | 56.6%† | – |
| Arena Instruction Following | Arena (LMArena) | 1475 | 1485 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1472 | 1497 |
| EQ-Bench 4 | EQ-Bench | 1197 | – |
| Arena Creative Writing | Arena (LMArena) | 1449 | 1468 |
| Arena Multi-turn | Arena (LMArena) | 1480 | 1493 |
| Arena Longer Queries | Arena (LMArena) | 1492 | 1498 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1283 | 1310 |
| LiveBench Design | LiveBench | – | 74.8%† |
| MMMU-Pro | Artificial Analysis | 73.3%† | 82.0%† |
| MMMU-Pro (Vals) | Vals AI | 83.6% | – |
| MortgageTax | Vals AI | 67.7% | – |
| GeoBench | GeoBench | 73.0% | 86.0%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 6.7% | – |
| Code2Video-AA | Artificial Analysis | – | 1019 |
| AA-3D | Artificial Analysis | – | 1032 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 80.0%† | 83.0% |
| Arena Document | Arena (LMArena) | 1478 | 1474 |
| MLCR | Artificial Analysis | 7.8%† | 13.9% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 152.9 | 158.2† |
| LiveBench 2.0 | LiveBench | – | 68.6%† |
| LiveBench 1.0 | LiveBench | 73.0%† | 81.6%† |
| AA Intelligence Index v5.0 | Artificial Analysis | – | 36.6 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 30.1† | 48.1 |
| AA Progress Index v1 | Artificial Analysis | 293.6† | 324.5 |
| Vals RSI Index | Vals AI | – | 19.6% |
| Vals Multimodal Index | Vals AI | 60.6% | – |
Data as of 2026-11-14. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Muse Spark 1.3 (max): 1 score revision.
- Claude Sonnet 4.6: 1 new result (GeoBench).
- Muse Spark 1.3 (max): 1 new result (MirrorCode).
- Muse Spark 1.3 (max): 1 new result (ForecastBench).
- Claude Sonnet 4.6: 1 new result (Arena Search).
- Muse Spark 1.3 (max): 1 score revision.
- Muse Spark 1.3 (max): 1 score revision.
- Muse Spark 1.3 (max): 1 score revision.
- Muse Spark 1.3 (max): BenchLeader Index 64.5 → 61.8.
- Muse Spark 1.3 (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $1.31/M to $2.39/M (81% up).
Related comparisons
- Claude Sonnet 4.6 vs Gemini 4 Carbon
- Claude Sonnet 4.6 vs GPT-6.1 Sol
- Muse Spark 1.3 vs Claude Fable 5.2
- Muse Spark 1.3 vs Gemini 4 Carbon
- Muse Spark 1.3 vs Claude Opus 5.5
- Muse Spark 1.3 vs GPT-6 Astra
- Claude Opus 4.6 vs Muse Spark 1.3
- Claude Sonnet 4.6 vs Claude Sonnet 5.5
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Claude Sonnet 4.6 vs Muse Spark 1.3: questions
- Is Muse Spark 1.3 better than Claude Sonnet 4.6?
- Muse Spark 1.3 (max) leads on quality: 61.5 vs 58.3. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 (max) is ahead overall as of 14 Nov 2026, but check the category scores for your use.
- Claude Sonnet 4.6 vs Muse Spark 1.3: which is cheaper, and will that change?
- Muse Spark 1.3 is cheaper today: $2.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Sonnet 4.6 or Muse Spark 1.3 better for coding?
- Muse Spark 1.3 scores higher in coding (60 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1522 for Claude Sonnet 4.6 against 1655 for Muse Spark 1.3.
- Which is faster, Claude Sonnet 4.6 or Muse Spark 1.3?
- Muse Spark 1.3 streams 3×+ faster (132 vs 44 output tokens per second, Artificial Analysis 7-day median).
- Is Claude Sonnet 4.6 or Muse Spark 1.3 better for agents and tool use?
- Muse Spark 1.3 scores higher in agentic tasks (65 vs 51 on the category index, where 50 is average). On Terminal-Bench 2.1 (Vals), the top shared agents & tools benchmark, it is 57.3% for Claude Sonnet 4.6 against 79.0% for Muse Spark 1.3.
More questions (4)
- Which is better for long documents?
- Both take about 1M tokens: Claude Sonnet 4.6 1,000,000, Muse Spark 1.3 1,048,576.
- Which has lower latency?
- Claude Sonnet 4.6 answers first: 0.7 s against 28.8 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.
- Do independent benchmarks agree on Claude Sonnet 4.6 vs Muse Spark 1.3?
- Across the 23 benchmarks both have, Claude Sonnet 4.6 leads 1, Muse Spark 1.3 leads 22. 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 Sep 2026.