Claude Sonnet 5.5 vs Muse Spark 1.2
Full profiles: Claude Sonnet 5.5 (Anthropic) and Muse Spark 1.2 (Meta): every benchmark, price and rank.
Updated · Data from 12 sources
As of 12 Nov 2026, Claude Sonnet 5.5 and Muse Spark 1.2 are neck and neck on quality (64.7 vs 61.6 on the BenchLeader Index, inside the ±5.7 margin), and Muse Spark 1.2 is 2.0× cheaper at $2.00 vs $4.00 per 1M tokens blended. Choose Claude Sonnet 5.5 for coding (72 vs 55), agents & tools (70 vs 56), and maths (71 vs 67); choose Muse Spark 1.2 for fast first answers (7.9 s vs 245.2 s) and knowledge (65 vs 58), where it also streams faster.
Key facts (as of 12 Nov 2026)
- Claude Sonnet 5.5 scores 64.7 on the BenchLeader Index and Muse Spark 1.2 scores 61.6 (BenchLeader, 12 Nov 2026).
- Claude Sonnet 5.5 costs $4.00 per 1M tokens blended (list price, 12 Nov 2026).
- Muse Spark 1.2 costs $2.00 per 1M tokens blended (list price, 12 Nov 2026).
- Muse Spark 1.2 streams faster than Claude Sonnet 5.5 (Artificial Analysis, 7-day median, 12 Nov 2026).
- Of the 25 benchmarks both models have, Claude Sonnet 5.5 leads 19 (BenchLeader, 12 Nov 2026).
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 | Claude Sonnet 5.5 | 72 vs 55 category score; SciCode 61.0% vs 57.4% | High |
| Agents & tool use | Claude Sonnet 5.5 | 70 vs 56 category score; Arena Agent 16 vs -8.2 | High |
| Maths | Claude Sonnet 5.5 | 71 vs 67 category score; LiveBench Mathematics 96.1% vs 91.2% | Medium |
| Reasoning | Either | 68 vs 68 category score; LiveBench 1.0 Reasoning 91.6% vs 90.0% | Either |
| Knowledge | Muse Spark 1.2 | 65 vs 58 category score; SimpleQA Verified 60.3% vs 46.5% | Medium |
| Long documents | Claude Sonnet 5.5 | 66 vs 64 category score; AA-LCR v1.1 82.7% vs 79.0% | Medium |
| Chat quality (human preference) | – | Only Muse Spark 1.2 has an Arena rating (69 category score) | Not comparable |
| Lowest cost | Muse Spark 1.2 | $2.00 vs $4.00 per 1M blended; agentic coding session $0.092 vs $0.160 | – |
| Fastest first answer | Muse Spark 1.2 | 7.9 s (Muse Spark 1.2 (xhigh)) vs 245.2 s (Claude Sonnet 5.5 (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
- Claude Sonnet 5.5 (max) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.7 vs 61.6, within the ±5.7 margin).
- Claude Sonnet 5.5 (max) is stronger in agents & tools, coding, long context, maths.
- Muse Spark 1.2 (xhigh) is stronger in knowledge, reasoning.
- Muse Spark 1.2 (xhigh) is 2.0× cheaper ($2.00 vs $4.00 per 1M blended).
- Muse Spark 1.2 (xhigh) streams 1.4× faster (204 vs 146 tokens per second).
At a glance
| Spec | Claude Sonnet 5.5 | Muse Spark 1.2 |
|---|---|---|
| Developer | Anthropic | Meta |
| Released | 28 Sep 2026 | 5 Aug 2026 |
| Context window (tokens) | 1,000,000 | 1,048,576 |
| Compared at | Claude Sonnet 5.5 (max) | Muse Spark 1.2 (xhigh) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $2.00 / $10.00 / $0.100 | $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 5.5 (max) | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 68.1 | 68.3 | level |
| Coding | 71.5 | 54.8 | Claude Sonnet 5.5 |
| Agents & tools | 69.9 | 55.5 | Claude Sonnet 5.5 |
| Maths | 71.3 | 67.2 | Claude Sonnet 5.5 |
| Knowledge | 57.6 | 64.5 | Muse Spark 1.2 |
| Human preference | – | 68.7 | not comparable |
| Multimodal | – | 65.3 | not comparable |
| Long context | 66.1 | 64.2 | Claude Sonnet 5.5 |
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, Multimodal, Human preference.
Where sources disagree
Across the 25 benchmarks both have, Claude Sonnet 5.5 leads 19, Muse Spark 1.2 leads 6. Every overall index that rates both puts Muse Spark 1.2 ahead.
| Overall index | Claude Sonnet 5.5 (max) | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| BenchLeader Index | 64.7 | 61.6 | neck and neck |
| Arena Text | 1473† | 1494 | Muse Spark 1.2 |
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 5.5 (max) | Muse Spark 1.2 (xhigh) |
|---|---|---|
| Blended price per 1M tokens | $4.00 | $2.00 |
| Input / output per 1M | $2.00 / $10.00 | $1.25 / $4.25 |
| Cached input per 1M | $0.100 | $0.150 |
| Price per task: chat reply | $0.0038 | $0.0018 |
| Price per task: summarize a 30-page report | $0.030 | $0.018 |
| Price per task: code edit | $0.027 | $0.014 |
| Price per task: agentic coding session | $0.160 | $0.092 |
| Price per task: structured extraction | $0.0060 | $0.0034 |
| Agentic coding session, input mostly cached | $0.074 | $0.043 |
| Cost per benchmark task (AA Index) | $10.02 | – |
| Output tokens per task (AA Index) | 285k | – |
| Of which reasoning | 206k | – |
| Time per task (AA Index) | 33 min | – |
| Output speed | 146 tok/s | 204 tok/s |
| Time to first answer | 245.2 s | 7.9 s |
| Time to a complete answer | 480.4 s | 24.3 s |
Each model is compared at its best-ranked reasoning-effort setting. Claude Sonnet 5.5 (max) scores 64.7 and takes 245 s to its first answer token; Claude Sonnet 5.5 (xhigh) scores 62.7 in 29 s, Claude Sonnet 5.5 (high) scores 58.1 in 11 s. Muse Spark 1.2 (xhigh) scores 61.6 and takes 8 s to its first answer token. 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
132 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 5.5 (max) | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.7 | 61.6 |
| Agents & tools score | BenchLeader | 69.9 | 55.5 |
| Coding score | BenchLeader | 71.5 | 54.8 |
| Knowledge score | BenchLeader | 57.6 | 64.5 |
| Long context score | BenchLeader | 66.1 | 64.2 |
| Maths score | BenchLeader | 71.3 | 67.2 |
| Reasoning score | BenchLeader | 68.1 | 68.3 |
| Human preference score | BenchLeader | – | 68.7 |
| Multimodal score | BenchLeader | – | 65.3 |
| Blended price $/M | BenchLeader | $4.00 | $2.00 |
| Output speed | BenchLeader | 146 tok/s | 204 tok/s |
| Time to first answer | BenchLeader | 245.2 s | 7.9 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 95.6% | – |
| Humanity's Last Exam | Scale AI / CAIS | 46.1%† | – |
| SimpleBench | SimpleBench | 75.9%† | 74.5%† |
| Arena Hard Prompts | Arena (LMArena) | 1498† | 1515 |
| LiveBench 2.0 Reasoning | LiveBench | 91.6%† | – |
| LiveBench 1.0 Reasoning | LiveBench | 91.6% | 90.0% |
| GPQA Diamond (AA) | Artificial Analysis | – | 90.4% |
| Humanity's Last Exam (AA) | Artificial Analysis | 55.0% | 45.5% |
| HLE-Diamond (AA) | Artificial Analysis | 53.3% | – |
| ARC-AGI-1 | ARC Prize | 96.5% | – |
| ARC-AGI-2 | ARC Prize | 83.9%† | – |
| ARC-AGI-3 | ARC Prize | 72.4%† | – |
| CritPt | Artificial Analysis | 31.4% | 17.7% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 59.0% | – |
| MysteryMechanism | Vals AI | 49.1%† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 59.0% | 27.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 65.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 68.3% | 48.4% |
| DTBench | Epoch AI Benchmarking Hub | 97.3% | 94.7% |
| Coding | |||
| SciCode | SciCode | 61.0% | 57.4% |
| WeirdML | WeirdML | – | 60.3% |
| FrontierCode | Cognition | 52.1%† | – |
| Arena Coding | Arena (LMArena) | 1516† | 1543 |
| Arena WebDev | Arena (LMArena) | 1773† | 1534 |
| LiveBench 2.0 Coding | LiveBench | 77.2%† | – |
Show all 132 benchmarks
| Metric | Publisher | Claude Sonnet 5.5 (max) | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| Coding | |||
| LiveBench 1.0 Coding | LiveBench | 91.4% | 77.5% |
| IOI | Vals AI | 83.1%† | 21.8% |
| SWE-bench (Vals) | Vals AI | – | 86.6% |
| Code Migration | Vals AI | 69.8%† | 29.9% |
| Code Migration v1.1 | Vals AI | 86.9%† | – |
| ProgramBench | Vals AI | 6.5%† | 0.5% |
| SWE-bench Multimodal | Vals AI | 58.3%† | – |
| Vibe Code Bench v1.1 | Vals AI | 92.4%† | 79.1% |
| MirrorCode | Epoch AI Benchmarking Hub | 97.8% | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 54.9% |
| CursorBench | Cursor | 55.5% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1819.1† | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 61.9% | 12.0% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 63.6% | 7.1% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 80.2% |
| Startrise Frontend | Startrise | 75.9%† | 70.3%† |
| GameBench 2 Overall | DuelLab GameBench 2 | 60.3† | 51.4† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 91.2† | 57.3 |
| Design Arena Website | Design Arena | 1313† | 1309† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 45.8% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 41.7% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 63.9% | – |
| APEX-Agents | Mercor | 75.5% | 45.4%† |
| Arena Agent | Arena (LMArena) | 16 | -8.2 |
| LiveBench Long Agentic | LiveBench | 63.4%† | – |
| LiveBench Browser | LiveBench | 89.3%† | – |
| LiveBench Agentic Coding | LiveBench | 56.3% | 57.6% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 83.2%† | 69.7% |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 66.9% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1838 | – |
| τ³-Banking (AA) | Artificial Analysis | – | 34.9% |
| Analyst Agent (AA) | Artificial Analysis | 57.5% | – |
| CyberBench | Vals AI | 59.6%† | 69.5% |
| Finance Agent v2 | Vals AI | 58.1%† | 60.6% |
| Finance Agent v2.1 | Vals AI | 67.3%† | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 10.4%† | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 2.9%† | 25.4% |
| Legal Research Bench | Vals AI | 48.1%† | 43.8% |
| SkillsBench | Vals AI | – | 53.0% |
| SREBench | Vals AI | 30.1%† | 0.0% |
| Tax Agent Bench | Vals AI | 42.0%† | 32.8% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 64.1%† | 6.1% |
| Terminal-Bench Science | Vals AI | 47.1%† | – |
| Vending-Bench 2 | Andon Labs | 11165.3† | – |
| AutomationBench | Artificial Analysis | 71.8% | 40.6% |
| GDP.pdf (AA) | Artificial Analysis | 25.8% | 17.4% |
| Harvey LAB-AA v1.1 | Harvey | 2.8% | – |
| EnterpriseOps-Gym | Artificial Analysis | – | 47.3% |
| AA-Briefcase v1.1 | Artificial Analysis | 1816 | 1324 |
| GDPx | GDPx by SemiAnalysis | 8.2% | – |
| Design Arena Agentic | Design Arena | 1281† | 1179† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 53.3% | – |
| FACTS Search | 86.8%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 88.8% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 80.5% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | – |
| ProofBench | Vals AI | 100.0% | 43.0%† |
| LiveBench Mathematics | LiveBench | 96.1% | 91.2% |
| Arena Maths | Arena (LMArena) | 1490† | 1490 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 46.5% | 60.3% |
| LiveBench 2.0 Data Analysis | LiveBench | 59.5%† | – |
| LiveBench Research | LiveBench | 88.0%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 59.5% | 76.5% |
| AA-Omniscience v1.1 | Artificial Analysis | 30.5 | – |
| MMLU-Pro | Vals AI | – | 88.3% |
| LegalBench | Vals AI | – | 85.3% |
| CorpFin | Vals AI | – | 70.9% |
| TaxEval | Vals AI | – | 80.4% |
| BioMysteryBench | Vals AI | 81.1%† | 64.8% |
| ClaimBench | Vals AI | 100.0%† | – |
| Excel Modeling Benchmark | Vals AI | 75.7%† | 57.0% |
| Excel Modeling Benchmark v1.1 | Vals AI | 75.9%† | – |
| MedCode | Vals AI | 52.9%† | 49.4% |
| MedScribe | Vals AI | 91.1%† | 90.1% |
| Public Benefits Bench v1.1 | Vals AI | 67.2%† | 68.5% |
| GDP.pdf | Epoch AI Benchmarking Hub | 31.4% | 16.0% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 51.5% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 56.7% | – |
| HealthBench Professional (AA) | OpenAI | 63.0% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 78.0% | 78.6% |
| LiveBench Instruction Following | LiveBench | 56.8% | 74.3% |
| Arena Instruction Following | Arena (LMArena) | 1480† | 1479 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1473† | 1494 |
| Arena Creative Writing | Arena (LMArena) | 1465† | 1443 |
| Arena Multi-turn | Arena (LMArena) | 1469† | 1512 |
| Arena Longer Queries | Arena (LMArena) | 1489† | 1491 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1284† | 1305 |
| LiveBench Design | LiveBench | 81.3%† | – |
| MMMU-Pro (Vals) | Vals AI | – | 86.1% |
| MortgageTax | Vals AI | – | 65.4% |
| SAGE | Vals AI | 88.0%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 39.3%† | – |
| Code2Video-AA | Artificial Analysis | 1443 | – |
| AA-3D | Artificial Analysis | 1204 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.7% | 79.0% |
| MLCR | Artificial Analysis | 41.7% | 7.2% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 166.6† | 155.0† |
| LiveBench 2.0 | LiveBench | 77.0%† | – |
| LiveBench 1.0 | LiveBench | 75.7% | 78.0% |
| AA Intelligence Index v5.0 | Artificial Analysis | 54.5 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 56 | 39.6 |
| AA Progress Index v1 | Artificial Analysis | 350.5 | 309.1 |
| Vals Index | Vals AI | 70.8† | – |
| Vals Finance Index | Vals AI | 64.5%† | – |
| Vals Science Index | Vals AI | 59.1%† | – |
| Vals Multimodal Index | Vals AI | – | 69.8%† |
| Vals Router Index | Vals AI | 69.0%† | – |
Data as of 2026-11-12. 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
- Claude Sonnet 5.5 (max): 1 new result (MirrorCode).
- Claude Sonnet 5.5 (max): 2 score revisions.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Muse Spark 1.2 (xhigh): 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 new result (MirrorCode).
- Muse Spark 1.2 (xhigh): 1 score revision.
- Muse Spark 1.2 (xhigh): BenchLeader Index 62.2 → 61.6.
- Claude Sonnet 5.5 (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $5.46/M to $10.02/M (83% up).
Related comparisons
- Claude Sonnet 5.5 vs Claude Fable 5.2
- Claude Sonnet 5.5 vs Gemini 4 Carbon
- Claude Sonnet 5.5 vs Claude Opus 5.5
- Muse Spark 1.2 vs Claude Fable 5.2
- Muse Spark 1.2 vs Gemini 4 Carbon
- Muse Spark 1.2 vs Claude Opus 5.5
- Muse Spark 1.2 vs GPT-6 Astra
- Claude Sonnet 5.5 vs Muse Spark 1.1
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Sonnet 5.5 vs Muse Spark 1.2: questions
- Is Claude Sonnet 5.5 better than Muse Spark 1.2?
- Claude Sonnet 5.5 (max) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.7 vs 61.6, within the ±5.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 12 Nov 2026, so check the category scores for your use.
- Claude Sonnet 5.5 vs Muse Spark 1.2: which is cheaper, and will that change?
- Muse Spark 1.2 is cheaper today: $2.00 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Sonnet 5.5 or Muse Spark 1.2 better for coding?
- Claude Sonnet 5.5 scores higher in coding (72 vs 55 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 61.0% for Claude Sonnet 5.5 against 57.4% for Muse Spark 1.2.
- Which is faster, Claude Sonnet 5.5 or Muse Spark 1.2?
- Muse Spark 1.2 streams faster (204 vs 146 output tokens per second, Artificial Analysis 7-day median).
- Is Claude Sonnet 5.5 or Muse Spark 1.2 better for agents and tool use?
- Claude Sonnet 5.5 scores higher in agentic tasks (70 vs 56 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 16 for Claude Sonnet 5.5 against -8.2 for Muse Spark 1.2.
More questions (4)
- Which is better for long documents?
- Claude Sonnet 5.5 scores higher on long-context benchmarks (66 vs 64). Both take about 1M tokens: Claude Sonnet 5.5 1,000,000, Muse Spark 1.2 1,048,576.
- Which has lower latency?
- Muse Spark 1.2 answers first: 7.9 s against 245.2 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 5.5 vs Muse Spark 1.2?
- Across the 25 benchmarks both have, Claude Sonnet 5.5 leads 19, Muse Spark 1.2 leads 6. Every overall index that rates both puts Muse Spark 1.2 ahead.
- When was Claude Sonnet 5.5 released?
- Claude Sonnet 5.5 was released on 28 Sep 2026.