Muse Spark 1.1 vs Qwen3.6 Plus
Full profiles: Muse Spark 1.1 (Meta) and Qwen3.6 Plus (Alibaba): every benchmark, price and rank.
Updated · Data from 10 sources
As of 16 Nov 2026, Muse Spark 1.1 and Qwen3.6 Plus are neck and neck on quality (62.2 vs 59.0 on the BenchLeader Index, inside the ±6.9 margin), and Qwen3.6 Plus is 1.8× cheaper at $1.13 vs $2.00 per 1M tokens blended. Choose Muse Spark 1.1 for coding (66 vs 51), knowledge (69 vs 57), and reasoning (68 vs 63) and fast first answers (1.8 s vs 44.4 s), where it also streams 3×+ faster; choose Qwen3.6 Plus for instruction following (73 vs 70) and agents & tools (53 vs 51).
Key facts (as of 16 Nov 2026)
- Muse Spark 1.1 scores 62.2 on the BenchLeader Index and Qwen3.6 Plus scores 59.0 (BenchLeader, 16 Nov 2026).
- Muse Spark 1.1 costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
- Qwen3.6 Plus costs $1.13 per 1M tokens blended (list price, 16 Nov 2026).
- Muse Spark 1.1 streams 3×+ faster than Qwen3.6 Plus (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 14 benchmarks both models have, Muse Spark 1.1 leads 14 (BenchLeader, 16 Nov 2026).
- On Arena WebDev, Muse Spark 1.1 is rated 1542 and Qwen3.6 Plus 1461 (LMArena, as published by 16 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 | Muse Spark 1.1 | 66 vs 51 category score; Arena WebDev 1542 vs 1461 | High |
| Agents & tool use | Qwen3.6 Plus | 53 vs 51 category score; Vending-Bench 2 5114.9 vs 6520.5 | Medium |
| Maths | Muse Spark 1.1 | 61 vs 58 category score; Arena Maths 1493 vs 1451 | Medium |
| Reasoning | Muse Spark 1.1 | 68 vs 63 category score; Arena Hard Prompts 1511 vs 1467 | Medium |
| Knowledge | Muse Spark 1.1 | 69 vs 57 category score; SimpleQA Verified 57.8% vs 44.1% | High |
| Images and other media | Muse Spark 1.1 | 64 vs 60 category score | Medium |
| Following instructions | Qwen3.6 Plus | 73 vs 70 category score; Arena Instruction Following 1435 vs 1473 | Medium |
| Chat quality (human preference) | Muse Spark 1.1 | 65 vs 62 on Arena votes | Medium |
| Lowest cost | Qwen3.6 Plus | $1.13 vs $2.00 per 1M blended; agentic coding session $0.042 vs $0.092 | – |
| Fastest first answer | Muse Spark 1.1 | 1.8 s (Muse Spark 1.1) vs 44.4 s (Qwen3.6 Plus) 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 Qwen3.6 Plus are neck and neck on quality (62.2 vs 59.0, within the ±6.9 margin).
- Muse Spark 1.1 is stronger in coding, human preference, knowledge, maths, multimodal, reasoning.
- Qwen3.6 Plus is stronger in agents & tools, instruction following.
- Qwen3.6 Plus is 1.8× cheaper ($1.13 vs $2.00 per 1M blended).
- Muse Spark 1.1 streams 3.7× faster (193 vs 52 tokens per second).
At a glance
| Spec | Muse Spark 1.1 | Qwen3.6 Plus |
|---|---|---|
| Developer | Meta | Alibaba |
| Released | 9 Jul 2026 | 31 Mar 2026 |
| Context window (tokens) | 1,048,576 | 1,000,000 |
| Compared at | Muse Spark 1.1 | Qwen3.6 Plus |
| Open weights | No | No |
| Price in / out / cached input per 1M | $1.25 / $4.25 / $0.150 | $0.500 / $3.00 / $0.050 |
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 | Qwen3.6 Plus | Leader |
|---|---|---|---|
| Reasoning | 67.8 | 62.9 | Muse Spark 1.1 |
| Coding | 65.8 | 50.8 | Muse Spark 1.1 |
| Agents & tools | 50.9 | 53.1 | Qwen3.6 Plus |
| Maths | 61.3 | 57.6 | Muse Spark 1.1 |
| Knowledge | 69.2 | 56.9 | Muse Spark 1.1 |
| Instruction following | 70.4 | 73.4 | Qwen3.6 Plus |
| Human preference | 64.5 | 62.4 | Muse Spark 1.1 |
| Multimodal | 63.6 | 60.3 | Muse Spark 1.1 |
| Long context | – | 63.8 | 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: Long context.
Where sources disagree
Across the 14 benchmarks both have, Muse Spark 1.1 leads 14, Qwen3.6 Plus leads 0. Every overall index that rates both puts Muse Spark 1.1 ahead.
| Overall index | Muse Spark 1.1 | Qwen3.6 Plus | Leader |
|---|---|---|---|
| BenchLeader Index | 62.2 | 59.0 | neck and neck |
| Arena Text | 1491 | 1443 | Muse Spark 1.1 |
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 | Muse Spark 1.1 | Qwen3.6 Plus |
|---|---|---|
| Blended price per 1M tokens | $2.00 | $1.13 |
| Input / output per 1M | $1.25 / $4.25 | $0.500 / $3.00 |
| Cached input per 1M | $0.150 | $0.050 |
| Price per task: chat reply | $0.0018 | $0.0011 |
| Price per task: summarize a 30-page report | $0.018 | $0.0078 |
| Price per task: code edit | $0.014 | $0.0075 |
| Price per task: agentic coding session | $0.092 | $0.042 |
| Price per task: structured extraction | $0.0034 | $0.0016 |
| Agentic coding session, input mostly cached | $0.043 | $0.022 |
| Output speed | 193 tok/s | 52 tok/s |
| Time to first answer | 1.8 s | 44.4 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 113.4 s |
Each model is compared at its best-ranked reasoning-effort setting. Muse Spark 1.1 scores 62.2 and takes 2 s to its first answer token; Muse Spark 1.1 (xhigh) scores 59.5 in 13 s. Qwen3.6 Plus scores 59.0 and takes 44 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
104 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 | Qwen3.6 Plus |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 62.2 | 59.0 |
| Agents & tools score | BenchLeader | 50.9 | 53.1 |
| Coding score | BenchLeader | 65.8 | 50.8 |
| Human preference score | BenchLeader | 64.5 | 62.4 |
| Instruction following score | BenchLeader | 70.4 | 73.4 |
| Knowledge score | BenchLeader | 69.2 | 56.9 |
| Maths score | BenchLeader | 61.3 | 57.6 |
| Multimodal score | BenchLeader | 63.6 | 60.3 |
| Reasoning score | BenchLeader | 67.8 | 62.9 |
| Long context score | BenchLeader | – | 63.8 |
| Blended price $/M | BenchLeader | $2.00 | $1.13 |
| Output speed | BenchLeader | 193 tok/s | 52 tok/s |
| Time to first answer | BenchLeader | 1.8 s | 44.4 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 88.4% |
| Arena Hard Prompts | Arena (LMArena) | 1511 | 1467 |
| LiveBench 1.0 Reasoning | LiveBench | 87.7%† | 75.8% |
| GPQA Diamond (AA) | Artificial Analysis | 89.8%† | 88.2% |
| Humanity's Last Exam (AA) | Artificial Analysis | 46.2%† | 27.9% |
| GPQA Diamond (Vals) | Vals AI | 91.2%† | 87.4% |
| CritPt | Artificial Analysis | 15.1%† | 2.9% |
| Arena Expert | Arena (LMArena) | 1504 | 1475 |
| Chess Puzzles | Epoch AI Benchmarking Hub | 34.0%† | 16.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 12.0%† |
| CL-bench | Epoch AI Benchmarking Hub | – | 20.3% |
| LMCA | Epoch AI Benchmarking Hub | 49.9%† | 33.1% |
| DTBench | Epoch AI Benchmarking Hub | 94.4%† | 81.9% |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 57.9% |
| SciCode | SciCode | 58.8% | 40.7% |
| Arena Coding | Arena (LMArena) | 1533 | 1496 |
| Arena WebDev | Arena (LMArena) | 1542 | 1461 |
| LiveBench 1.0 Coding | LiveBench | 77.2%† | 78.2% |
| SciCode (AA) | Artificial Analysis | 58.8%† | – |
| LiveCodeBench | Vals AI | 85.9%† | 86.0% |
| SWE-bench (Vals) | Vals AI | 82.0%† | 73.4% |
| SWE-Bench Pro | Scale AI SEAL | 61.5% | – |
| Code Migration | Vals AI | 31.1%† | 11.1% |
| ProgramBench | Vals AI | 0.0%† | 0.0% |
| Vibe Code Bench v1.1 | Vals AI | 72.2%† | 25.6% |
Show all 104 benchmarks
| Metric | Publisher | Muse Spark 1.1 | Qwen3.6 Plus |
|---|---|---|---|
| Coding | |||
| SWE-Bench Pro (private) | Scale AI SEAL | 51.5% | – |
| SWE Atlas v1.0: Codebase QnA | Scale AI SEAL | 42.2%† | – |
| SWE Atlas v1.0: 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% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 670.1 |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 6.1%† | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 77.9%† | 61.4% |
| Design Arena Website | Design Arena | 1263 | 1234 |
| Agents & tools | |||
| APEX-Agents | Mercor | 31.8% | – |
| Arena Agent | Arena (LMArena) | -8 | – |
| LiveBench Agentic Coding | LiveBench | 58.5%† | 41.4% |
| Terminal-Bench Hard | Artificial Analysis | – | 43.9% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 97.7% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 69.3%† | 53.2% |
| MCP Atlas | Scale AI SEAL | 88.1% | – |
| τ³-bench Banking | τ²-bench | 40.5%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 1216† | 997 |
| τ³-Banking (AA) | Artificial Analysis | 31.8%† | 20.8% |
| Finance Agent v2 | Vals AI | 57.2%† | 40.9% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 20.0%† | 1.3% |
| Legal Research Bench | Vals AI | 38.0%† | 14.9% |
| SkillsBench | Vals AI | 59.2%† | – |
| Tax Agent Bench | Vals AI | – | 7.7% |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 44.9% |
| Time Horizon Index: KSP | Vals AI | 1.7%† | – |
| Arena Agent Task Completion | Arena (LMArena) | -6.5 | – |
| GBAEval | Epoch AI Benchmarking Hub | 7.9% | – |
| Vending-Bench 2 | Andon Labs | 6520.5 | 5114.9 |
| AutomationBench | Artificial Analysis | 38.9%† | – |
| GDP.pdf (AA) | Artificial Analysis | 14.4%† | – |
| AA-Briefcase v1.1 | Artificial Analysis | 851† | – |
| Design Arena Agentic | Design Arena | 1172 | – |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 38.3% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 93.3% |
| ProofBench | Vals AI | 39.0% | – |
| LiveBench Mathematics | LiveBench | 87.1%† | 83.7% |
| AIME (Vals) | Vals AI | – | 94.6% |
| Arena Maths | Arena (LMArena) | 1493 | 1451 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 57.8% | 44.1% |
| LiveBench 1.0 Data Analysis | LiveBench | 72.5%† | 69.9% |
| MMLU-Pro | Vals AI | 88.7%† | 87.7% |
| LegalBench | Vals AI | 85.0%† | 84.2% |
| CorpFin | Vals AI | 71.3%† | 61.9% |
| TaxEval | Vals AI | 79.7%† | 74.7% |
| PRBench Finance | Scale AI SEAL | 55.0% | – |
| PRBench Legal | Scale AI SEAL | 57.0% | – |
| MultiNRC | Scale AI SEAL | 65.6% | – |
| CaseLaw v2 | Vals AI | – | 51.5% |
| Excel Modeling Benchmark | Vals AI | 56.4%† | 32.9% |
| MedCode | Vals AI | – | 36.9% |
| MedScribe | Vals AI | 88.9%† | 77.0% |
| Public Benefits Bench v1.1 | Vals AI | 61.3%† | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 15.0% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 74.3%† | 75.0% |
| LiveBench Instruction Following | LiveBench | 69.6%† | 58.3% |
| IFBench | Artificial Analysis | – | 75.2% |
| MultiChallenge | Scale AI SEAL | 75.3% | – |
| Arena Instruction Following | Arena (LMArena) | 1473 | 1435 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1491 | 1443 |
| EQ-Bench 4 | EQ-Bench | 1244 | – |
| EQ-Bench Creative Writing v3 | EQ-Bench | 1928 | – |
| Arena Creative Writing | Arena (LMArena) | 1443 | 1407 |
| Arena Multi-turn | Arena (LMArena) | 1497 | 1445 |
| Arena Longer Queries | Arena (LMArena) | 1481 | 1455 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1292 | – |
| MMMU-Pro | Artificial Analysis | – | 78.0% |
| MMMU-Pro (Vals) | Vals AI | 86.6%† | 84.2% |
| MortgageTax | Vals AI | 66.1%† | 68.0% |
| VTB | Scale AI SEAL | 44.8% | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 77.7%† | 78.3% |
| Arena Document | Arena (LMArena) | 1480 | – |
| MLCR | Artificial Analysis | 7.2%† | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 154.9 | 148.9 |
| LiveBench 1.0 | LiveBench | 75.3%† | 68.9% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 33.7† | 27.0 |
| AA Progress Index v1 | Artificial Analysis | 302.7† | 283.4 |
| Vals Multimodal Index | Vals AI | 66.7%† | 51.5% |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 12.4% | – |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
What changed
- Qwen3.6 Plus: 1 new result (GDPval-AA v2.1).
- Muse Spark 1.1: 1 score revision.
- Qwen3.6 Plus: 2 score revisions.
- Qwen3.6 Plus: Qwen3.6 Plus cached input price moved from $0.028/M to $0.050/M (81% up).
- Qwen3.6 Plus: Qwen3.6 Plus cached input price moved from $0.050/M to $0.028/M (45% down).
- Qwen3.6 Plus: Qwen3.6 Plus cached input price moved from $0.028/M to $0.050/M (81% up).
- Qwen3.6 Plus: Qwen3.6 Plus cached input price moved from $0.050/M to $0.028/M (45% down).
- Muse Spark 1.1: 2 score revisions.
- Qwen3.6 Plus: 1 new result (AA Progress Index v1).
- Qwen3.6 Plus: BenchLeader Index 59.7 → 59.2.
Related comparisons
- Muse Spark 1.1 vs Claude Fable 5.2
- Muse Spark 1.1 vs Gemini 4 Carbon
- Muse Spark 1.1 vs Claude Opus 5.5
- Muse Spark 1.1 vs GPT-6 Astra
- Muse Spark 1.1 vs Claude Fable 5.1
- Muse Spark 1.1 vs GPT-6.1 Sol
- Muse Spark 1.1 vs Claude Fable 5
- Muse Spark 1.1 vs GPT-5.6 Sol
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Muse Spark 1.1 vs Qwen3.6 Plus: questions
- Is Muse Spark 1.1 better than Qwen3.6 Plus?
- Muse Spark 1.1 and Qwen3.6 Plus are neck and neck on quality (62.2 vs 59.0, within the ±6.9 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
- Muse Spark 1.1 vs Qwen3.6 Plus: which is cheaper, and will that change?
- Qwen3.6 Plus is cheaper today: $1.13 against $2.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Muse Spark 1.1 or Qwen3.6 Plus better for coding?
- Muse Spark 1.1 scores higher in coding (66 vs 51 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1542 for Muse Spark 1.1 against 1461 for Qwen3.6 Plus.
- Which is faster, Muse Spark 1.1 or Qwen3.6 Plus?
- Muse Spark 1.1 streams 3×+ faster (193 vs 52 output tokens per second, Artificial Analysis 7-day median).
- Is Muse Spark 1.1 or Qwen3.6 Plus better for agents and tool use?
- Qwen3.6 Plus scores higher in agentic tasks (53 vs 51 on the category index, where 50 is average).
More questions (4)
- Which is better for long documents?
- Both take about 1M tokens: Muse Spark 1.1 1,048,576, Qwen3.6 Plus 1,000,000.
- Which has lower latency?
- Muse Spark 1.1 answers first: 1.8 s against 44.4 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 Muse Spark 1.1 vs Qwen3.6 Plus?
- Across the 14 benchmarks both have, Muse Spark 1.1 leads 14, Qwen3.6 Plus leads 0. Every overall index that rates both puts Muse Spark 1.1 ahead.
- When was Muse Spark 1.1 released?
- Muse Spark 1.1 was released on 9 Jul 2026.