Kimi K3.1 Pro vs Muse Spark 1.1
Full profiles: Kimi K3.1 Pro (Moonshot AI) and Muse Spark 1.1 (Meta): every benchmark, price and rank.
Updated · Data from 11 sources
As of 10 Nov 2026, Kimi K3.1 Pro and Muse Spark 1.1 are neck and neck on quality (61.2 vs 62.2 on the BenchLeader Index, inside the ±6.6 margin), and Muse Spark 1.1 is 2.0× cheaper at $2.00 vs $4.00 per 1M tokens blended. Choose Kimi K3.1 Pro for agents & tools (67 vs 51), maths (73 vs 61), and multimodal (66 vs 64); choose Muse Spark 1.1 for fast first answers (1.7 s vs 161.8 s) and reasoning (68 vs 60), knowledge (69 vs 62), and coding (66 vs 60), where it also streams 3×+ faster.
Key facts (as of 10 Nov 2026)
- Kimi K3.1 Pro scores 61.2 on the BenchLeader Index and Muse Spark 1.1 scores 62.2 (BenchLeader, 10 Nov 2026).
- Kimi K3.1 Pro costs $4.00 per 1M tokens blended (list price, 10 Nov 2026).
- Muse Spark 1.1 costs $2.00 per 1M tokens blended (list price, 10 Nov 2026).
- Muse Spark 1.1 streams 3×+ faster than Kimi K3.1 Pro (Artificial Analysis, 7-day median, 10 Nov 2026).
- Of the 6 benchmarks both models have, Kimi K3.1 Pro leads 6 (BenchLeader, 10 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 60 category score; SciCode 58.8% vs 60.8% | Medium |
| Agents & tool use | Kimi K3.1 Pro | 67 vs 51 category score; APEX-Agents 65.5% vs 31.8% | High |
| Maths | Kimi K3.1 Pro | 73 vs 61 category score; ProofBench 91.0% vs 39.0% | High |
| Reasoning | Muse Spark 1.1 | 68 vs 60 category score | High |
| Knowledge | Muse Spark 1.1 | 69 vs 62 category score | High |
| Images and other media | Kimi K3.1 Pro | 66 vs 64 category score | Medium |
| Chat quality (human preference) | – | Only Muse Spark 1.1 has an Arena rating (65 category score) | Not comparable |
| Lowest cost | Muse Spark 1.1 | $2.00 vs $4.00 per 1M blended; agentic coding session $0.092 vs $0.160 | – |
| Fastest first answer | Muse Spark 1.1 | 1.7 s (Muse Spark 1.1) vs 161.8 s (Kimi K3.1 Pro) 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
- Kimi K3.1 Pro and Muse Spark 1.1 are neck and neck on quality (61.2 vs 62.2, within the ±6.6 margin).
- Kimi K3.1 Pro is stronger in agents & tools, composite, long context, maths, multimodal.
- Muse Spark 1.1 is stronger in coding, knowledge, reasoning, human preference, instruction following.
- Muse Spark 1.1 is 2.0× cheaper ($2.00 vs $4.00 per 1M blended).
- Muse Spark 1.1 streams 5.8× faster (185 vs 32 tokens per second).
At a glance
| Spec | Kimi K3.1 Pro | Muse Spark 1.1 |
|---|---|---|
| Developer | Moonshot AI | Meta |
| Released | 23 Oct 2026 | 9 Jul 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Kimi K3.1 Pro | Muse Spark 1.1 |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $2.00 / $10.00 / $0.200 | $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 | Kimi K3.1 Pro | Muse Spark 1.1 | Leader |
|---|---|---|---|
| Reasoning | 59.6 | 67.8 | Muse Spark 1.1 |
| Coding | 59.8 | 66.2 | Muse Spark 1.1 |
| Agents & tools | 67.1 | 51.0 | Kimi K3.1 Pro |
| Maths | 73.4 | 61.3 | Kimi K3.1 Pro |
| Knowledge | 61.5 | 69.4 | Muse Spark 1.1 |
| Instruction following | – | 70.3 | not comparable |
| Human preference | – | 64.5 | not comparable |
| Multimodal | 66.4 | 63.6 | Kimi K3.1 Pro |
| Long context | 68.0 | – | not comparable |
| Composite | 54.8 | – | 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: Instruction following, Long context, Human preference.
Where sources disagree
Across the 6 benchmarks both have, Kimi K3.1 Pro leads 6, Muse Spark 1.1 leads 0. Every overall index that rates both puts Muse Spark 1.1 ahead.
| Overall index | Kimi K3.1 Pro | Muse Spark 1.1 | Leader |
|---|---|---|---|
| BenchLeader Index | 61.2 | 62.2 | neck and neck |
| Arena Text | 1483† | 1491 | 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 | Kimi K3.1 Pro | Muse Spark 1.1 |
|---|---|---|
| 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 | $0.200 | $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 | $0.079 | $0.043 |
| Cost per benchmark task (AA Index) | $3.68 | – |
| Output tokens per task (AA Index) | 72k | – |
| Of which reasoning | 44k | – |
| Time per task (AA Index) | 38 min | – |
| Output speed | 32 tok/s | 185 tok/s |
| Time to first answer | 161.8 s | 1.7 s |
| Time to a complete answer | 397.6 s | – |
Each model is compared at its best-ranked reasoning-effort setting. Kimi K3.1 Pro scores 61.2 and takes 162 s to its first answer token; Kimi K3.1 Pro (max) scores 60.4 in 162 s. Muse Spark 1.1 scores 62.2 and takes 2 s to its first answer token; Muse Spark 1.1 (xhigh) scores 59.6 in 13 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
127 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 | Kimi K3.1 Pro | Muse Spark 1.1 |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 61.2 | 62.2 |
| Agents & tools score | BenchLeader | 67.1 | 51.0 |
| Coding score | BenchLeader | 59.8 | 66.2 |
| Composite score | BenchLeader | 54.8 | – |
| Knowledge score | BenchLeader | 61.5 | 69.4 |
| Long context score | BenchLeader | 68.0 | – |
| Maths score | BenchLeader | 73.4 | 61.3 |
| Multimodal score | BenchLeader | 66.4 | 63.6 |
| Reasoning score | BenchLeader | 59.6 | 67.8 |
| Human preference score | BenchLeader | – | 64.5 |
| Instruction following score | BenchLeader | – | 70.3 |
| Blended price $/M | BenchLeader | $4.00 | $2.00 |
| Output speed | BenchLeader | 32 tok/s | 185 tok/s |
| Time to first answer | BenchLeader | 161.8 s | 1.7 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | 1501† | 1511 |
| LiveBench 2.0 Reasoning | LiveBench | 91.1% | – |
| LiveBench 1.0 Reasoning | LiveBench | – | 87.7%† |
| GPQA Diamond (AA) | Artificial Analysis | – | 89.8%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 52.5% | 46.2%† |
| HLE-Diamond (AA) | Artificial Analysis | 37.3% | – |
| GPQA Diamond (Vals) | Vals AI | – | 91.2%† |
| CritPt | Artificial Analysis | 24.6% | 15.1%† |
| CritPt v2 hard subset (AA) | Artificial Analysis | 49.5% | – |
| MysteryMechanism | Vals AI | 26.1%† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 34.0%† |
| LMCA | Epoch AI Benchmarking Hub | 57.6%† | 49.9%† |
| DTBench | Epoch AI Benchmarking Hub | 93.3%† | 94.4%† |
| Coding | |||
| SciCode | SciCode | 60.8% | 58.8% |
| Arena Coding | Arena (LMArena) | 1526† | 1533 |
| Arena WebDev | Arena (LMArena) | 1688† | 1542 |
| LiveBench 2.0 Coding | LiveBench | 67.8% | – |
| LiveBench 1.0 Coding | LiveBench | – | 77.2%† |
| LiveCodeBench | Vals AI | – | 85.9%† |
| IOI | Vals AI | 81.9%† | – |
| SWE-bench (Vals) | Vals AI | – | 82.0%† |
| SWE-Bench Pro | Scale AI SEAL | – | 61.5% |
| Code Migration | Vals AI | – | 31.1%† |
| ProgramBench | Vals AI | – | 0.0%† |
| Vibe Code Bench v1.1 | Vals AI | 84.9%† | 72.2%† |
Show all 127 benchmarks
| Metric | Publisher | Kimi K3.1 Pro | Muse Spark 1.1 |
|---|---|---|---|
| Coding | |||
| 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% |
| ALE-Bench | Epoch AI Benchmarking Hub | 1932.8† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 67.2% | 6.1%† |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 77.9%† |
| Startrise Frontend | Startrise | 82.5% | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 78.2 | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 84.0† | – |
| Design Arena Website | Design Arena | 1320 | 1266 |
| FrontierCode 1.1 (AA) | Artificial Analysis | 47.1% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 25.4% | – |
| Agents & tools | |||
| APEX-Agents | Mercor | 65.5% | 31.8% |
| Arena Agent | Arena (LMArena) | 5.2† | -7.9 |
| LiveBench Long Agentic | LiveBench | 38.7% | – |
| LiveBench Browser | LiveBench | 75.9% | – |
| LiveBench Agentic Coding | LiveBench | – | 58.5%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 69.3%† |
| MCP Atlas | Scale AI SEAL | – | 88.1% |
| τ³-bench Banking | τ²-bench | – | 40.5%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 67.3% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1861 | – |
| τ³-Banking (AA) | Artificial Analysis | – | 31.8%† |
| Analyst Agent (AA) | Artificial Analysis | 38.8% | – |
| Finance Agent v2 | Vals AI | – | 57.2%† |
| Finance Agent v2.1 | Vals AI | 61.5%† | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 11.7%† | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 20.0%† |
| Legal Research Bench | Vals AI | 37.5%† | 38.0%† |
| SkillsBench | Vals AI | – | 59.2%† |
| SREBench | Vals AI | 27.1%† | – |
| Tax Agent Bench | Vals AI | 24.9%† | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 63.6%† | – |
| Terminal-Bench Science | Vals AI | 31.4%† | – |
| 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 | 73.3% | 38.9%† |
| GDP.pdf (AA) | Artificial Analysis | 31.4% | 14.4%† |
| AA-Briefcase v1.1 | Artificial Analysis | 1674 | – |
| Design Arena Agentic | Design Arena | 1281 | 1165 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 34.3% | – |
| CWE-Bench (AA) | Artificial Analysis | 60.8% | – |
| DeepSec-Bench (AA) | Artificial Analysis | 36.7% | – |
| CyberGym end-to-end (AA) | Artificial Analysis | 94.7% | – |
| Maths | |||
| ProofBench | Vals AI | 91.0% | 39.0% |
| LiveBench Mathematics | LiveBench | – | 87.1%† |
| Arena Maths | Arena (LMArena) | – | 1493 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 57.8% |
| LiveBench 2.0 Data Analysis | LiveBench | 79.1% | – |
| LiveBench Research | LiveBench | 82.1% | – |
| LiveBench 1.0 Data Analysis | LiveBench | – | 72.5%† |
| AA-Omniscience v1.1 | Artificial Analysis | 29.9 | – |
| 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% |
| PRBench Legal | Scale AI SEAL | – | 57.0% |
| MultiNRC | Scale AI SEAL | – | 65.6% |
| BioMysteryBench | Vals AI | 75.6%† | – |
| Excel Modeling Benchmark | Vals AI | – | 56.4%† |
| Excel Modeling Benchmark v1.1 | Vals AI | 70.0%† | – |
| MedScribe | Vals AI | – | 88.9%† |
| Public Benefits Bench v1.1 | Vals AI | – | 61.3%† |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 15.0% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 48.9% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 62.7% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 74.3%† |
| LiveBench Instruction Following | LiveBench | – | 69.6%† |
| MultiChallenge | Scale AI SEAL | – | 75.3% |
| Arena Instruction Following | Arena (LMArena) | 1485† | 1473 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1483† | 1491 |
| EQ-Bench 4 | EQ-Bench | – | 1244 |
| Arena Creative Writing | Arena (LMArena) | 1457† | 1443 |
| Arena Multi-turn | Arena (LMArena) | 1473† | 1497 |
| Arena Longer Queries | Arena (LMArena) | 1488† | 1480 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1292 |
| LiveBench Design | LiveBench | 73.7% | – |
| MMMU-Pro | Artificial Analysis | 83.9% | – |
| MMMU-Pro (Vals) | Vals AI | – | 86.6%† |
| MortgageTax | Vals AI | – | 66.1%† |
| VTB | Scale AI SEAL | – | 44.8% |
| AA-3D | Artificial Analysis | 1112 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 86.3% | 77.7%† |
| Arena Document | Arena (LMArena) | – | 1480 |
| MLCR | Artificial Analysis | 38.3% | 7.2%† |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 162.0 | 154.8 |
| LiveBench 2.0 | LiveBench | 68.7% | – |
| LiveBench 1.0 | LiveBench | – | 75.3%† |
| AA Intelligence Index v5.0 | Artificial Analysis | 46.5 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 55.1 | 33.7† |
| AA Progress Index v1 | Artificial Analysis | 340.7 | 302.7† |
| Vals Index | Vals AI | 62.5† | – |
| Vals Finance Index | Vals AI | 56.0%† | – |
| Vals Science Index | Vals AI | 44.4%† | – |
| Vals Multimodal Index | Vals AI | – | 66.7%† |
| AA Cyber Index | Artificial Analysis | 64.1 | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 12.4% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 33.3 | – |
Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Kimi K3.1 Pro: 2 new results (APEX-Agents, Epoch Capabilities Index).
- Kimi K3.1 Pro: BenchLeader Index 61.8 → 61.2.
- Kimi K3.1 Pro: 5 score revisions.
- Kimi K3.1 Pro: BenchLeader Index 61.3 → 61.8.
- Muse Spark 1.1: 1 score revision.
- Kimi K3.1 Pro: 1 new result (GameBench 2 Overall); 1 score revision.
- Kimi K3.1 Pro: 1 score revision.
- Kimi K3.1 Pro: BenchLeader Index 59.3 → 61.3.
- Kimi K3.1 Pro: 3 new results (SciCode, ProofBench, Startrise Frontend).
- Muse Spark 1.1: 2 score revisions.
Related comparisons
- Kimi K3.1 Pro vs Claude Fable 5.2
- Kimi K3.1 Pro vs Claude Opus 5.5
- Kimi K3.1 Pro vs Gemini 4 Carbon
- Muse Spark 1.1 vs Claude Fable 5.2
- Muse Spark 1.1 vs Claude Opus 5.5
- Muse Spark 1.1 vs Gemini 4 Carbon
- Muse Spark 1.1 vs GPT-6 Astra
- Kimi K3 vs Muse Spark 1.1
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Kimi K3.1 Pro vs Muse Spark 1.1: questions
- Is Kimi K3.1 Pro better than Muse Spark 1.1?
- Kimi K3.1 Pro and Muse Spark 1.1 are neck and neck on quality (61.2 vs 62.2, within the ±6.6 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 10 Nov 2026, so check the category scores for your use.
- Kimi K3.1 Pro vs Muse Spark 1.1: which is cheaper, and will that change?
- Muse Spark 1.1 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 Kimi K3.1 Pro or Muse Spark 1.1 better for coding?
- Muse Spark 1.1 scores higher in coding (66 vs 60 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 60.8% for Kimi K3.1 Pro against 58.8% for Muse Spark 1.1.
- Which is faster, Kimi K3.1 Pro or Muse Spark 1.1?
- Muse Spark 1.1 streams 3×+ faster (185 vs 32 output tokens per second, Artificial Analysis 7-day median).
- Is Kimi K3.1 Pro or Muse Spark 1.1 better for agents and tool use?
- Kimi K3.1 Pro scores higher in agentic tasks (67 vs 51 on the category index, where 50 is average). On APEX-Agents, the top shared agents & tools benchmark, it is 65.5% for Kimi K3.1 Pro against 31.8% for Muse Spark 1.1.
More questions (4)
- Which is better for long documents?
- Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Muse Spark 1.1 answers first: 1.7 s against 161.8 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 Kimi K3.1 Pro vs Muse Spark 1.1?
- Across the 6 benchmarks both have, Kimi K3.1 Pro leads 6, Muse Spark 1.1 leads 0. Every overall index that rates both puts Muse Spark 1.1 ahead.
- When was Kimi K3.1 Pro released?
- Kimi K3.1 Pro was released on 23 Oct 2026.