Kimi K3.1 Pro vs Muse Spark 1.2
Full profiles: Kimi K3.1 Pro (Moonshot AI) and Muse Spark 1.2 (Meta): every benchmark, price and rank.
Updated · Data from 7 sources
As of 24 Oct 2026, Kimi K3.1 Pro and Muse Spark 1.2 (xhigh) are neck and neck on quality (66.8 vs 63.2 on the BenchLeader Index, inside the ±7.8 margin of error), and Muse Spark 1.2 (xhigh) costs 2.0× less, which makes it the better buy for most workloads. Kimi K3.1 Pro leads in every category we measure both in.
Kimi K3.1 Pro benchmarks Moonshot AI
Muse Spark 1.2 benchmarks xhigh MetaOpen in the comparison toolWhich 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 |
|---|---|---|---|
| Agents & tool use | Kimi K3.1 Pro | 67 vs 55 category score; AutomationBench 73.3% vs 40.6% | High |
| Reasoning | Kimi K3.1 Pro | 81 vs 69 category score; CritPt 24.6% vs 17.7% | High |
| Knowledge | Kimi K3.1 Pro | 75 vs 67 category score; AA-Omniscience 29.5 vs 27.2 | High |
| Long documents | Kimi K3.1 Pro | 68 vs 65 category score; AA-LCR 86.3% vs 79.0% | Medium |
| Images and other media | Kimi K3.1 Pro | 67 vs 65 category score | 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 | 17.6 s (Muse Spark 1.2 (xhigh)) vs 27.7 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 1.2 (xhigh) are neck and neck on quality (66.8 vs 63.2, within the ±7.8 margin).
- Kimi K3.1 Pro is stronger in agents & tools, composite, knowledge, long context, multimodal, reasoning.
- Muse Spark 1.2 (xhigh) is stronger in coding, human preference, maths.
- Muse Spark 1.2 (xhigh) is 2.0× cheaper ($2.00 vs $4.00 per 1M blended).
- Muse Spark 1.2 (xhigh) streams 3.8× faster (307 vs 81 tokens per second).
At a glance
| Spec | Kimi K3.1 Pro | Muse Spark 1.2 |
|---|---|---|
| Developer | Moonshot AI | Meta |
| Released | 23 Oct 2026 | 5 Aug 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Kimi K3.1 Pro | Muse Spark 1.2 (xhigh) |
| Open weights | No | 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 1.2 (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 81.3 | 69.3 | Kimi K3.1 Pro |
| Coding | – | 55.2 | not comparable |
| Agents & tools | 67.3 | 55.0 | Kimi K3.1 Pro |
| Maths | – | 67.3 | not comparable |
| Knowledge | 74.8 | 66.7 | Kimi K3.1 Pro |
| Human preference | – | 68.6 | not comparable |
| Multimodal | 67.0 | 65.2 | Kimi K3.1 Pro |
| Long context | 68.3 | 64.5 | Kimi K3.1 Pro |
| Composite | 75.8 | 73.8 | Kimi K3.1 Pro |
Where sources disagree
Across the 10 benchmarks both have, Kimi K3.1 Pro leads 9, Muse Spark 1.2 leads 1. Every overall index that rates both puts Kimi K3.1 Pro ahead.
| Overall index | Kimi K3.1 Pro | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| BenchLeader Index | 66.8 | 63.2 | neck and neck |
| AA Intelligence Index v4.3.2 | 55.1 | 39.6 | Kimi K3.1 Pro |
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 | Kimi K3.1 Pro | 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 | $0.200 | $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 |
| Cost to run a full benchmark suite | $2.11 | $0.975 |
| Output speed | 81 tok/s | 307 tok/s |
| Time to first answer | 27.7 s | 17.6 s |
| Time to a complete answer | 33.9 s | 19.2 s |
Per token is not per task: on Artificial Analysis' full suite Kimi K3.1 Pro cost $2.11 and Muse Spark 1.2 (xhigh) $0.975, because Kimi K3.1 Pro used about 1.1× as many tokens for the same work.
Each model is compared at its best-ranked reasoning-effort setting. Kimi K3.1 Pro scores 66.8 and takes 28 s to its first answer token. Muse Spark 1.2 (xhigh) scores 63.2 and takes 18 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
92 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 1.2 (xhigh) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 66.8 | 63.2 |
| Agents & tools score | BenchLeader | 67.3 | 55.0 |
| Composite score | BenchLeader | 75.8 | 73.8 |
| Knowledge score | BenchLeader | 74.8 | 66.7 |
| Long context score | BenchLeader | 68.3 | 64.5 |
| Multimodal score | BenchLeader | 67.0 | 65.2 |
| Reasoning score | BenchLeader | 81.3 | 69.3 |
| Coding score | BenchLeader | – | 55.2 |
| Human preference score | BenchLeader | – | 68.6 |
| Maths score | BenchLeader | – | 67.3 |
| Blended price $/M | BenchLeader | $4.00 | $2.00 |
| Output speed | BenchLeader | 81 tok/s | 307 tok/s |
| Time to first answer | BenchLeader | 27.7 s | 17.6 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| SimpleBench | SimpleBench | – | 74.5%† |
| Arena Hard Prompts | Arena (LMArena) | – | 1512 |
| LiveBench 2.0 Reasoning | LiveBench | 91.1% | 90.0%† |
| LiveBench 1.0 Reasoning | LiveBench | – | 90.0% |
| GPQA Diamond (AA) | Artificial Analysis | – | 90.4% |
| Humanity's Last Exam (AA) | Artificial Analysis | 52.5% | 45.5% |
| CritPt | Artificial Analysis | 24.6% | 17.7% |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 27.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 48.4% |
| DTBench | Epoch AI Benchmarking Hub | – | 94.7% |
| Coding | |||
| SciCode | SciCode | – | 57.4% |
| WeirdML | WeirdML | – | 60.3% |
| Arena Coding | Arena (LMArena) | – | 1541 |
| Arena WebDev | Arena (LMArena) | – | 1534 |
| LiveBench 2.0 Coding | LiveBench | 81.8% | 78.2%† |
| LiveBench 1.0 Coding | LiveBench | – | 77.5% |
| SciCode (AA) | Artificial Analysis | 60.8% | 57.4% |
| IOI | Vals AI | – | 21.8% |
| SWE-bench (Vals) | Vals AI | – | 86.6% |
| Code Migration | Vals AI | – | 29.9% |
| ProgramBench | Vals AI | – | 0.5% |
| Vibe Code Bench v1.1 | Vals AI | – | 79.1% |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 54.9% |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 12.0% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 67.2% | 7.1% |
Show all 92 benchmarks
| Metric | Publisher | Kimi K3.1 Pro | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| Coding | |||
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 80.2% |
| Startrise Frontend | Startrise | – | 70.3%† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 47.1% | – |
| Agents & tools | |||
| APEX-Agents | Mercor | – | 45.4%† |
| Arena Agent | Arena (LMArena) | – | -6.8 |
| LiveBench Long Agentic | LiveBench | 49.5% | 21.3%† |
| LiveBench Browser | LiveBench | 80.0% | 36.0%† |
| LiveBench Agentic Coding | LiveBench | – | 57.6% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 69.7% |
| GDPval-AA v2.1 | Artificial Analysis | 67.3% | – |
| τ³-Banking (AA) | Artificial Analysis | – | 34.9% |
| CyberBench | Vals AI | – | 69.5% |
| Finance Agent v2 | Vals AI | – | 60.6% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 25.4% |
| Legal Research Bench | Vals AI | – | 43.8% |
| SkillsBench | Vals AI | – | 53.0% |
| SREBench | Vals AI | – | 0.0% |
| Tax Agent Bench | Vals AI | – | 32.8% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 6.1% |
| AutomationBench | Artificial Analysis | 73.3% | 40.6% |
| GDP.pdf (AA) | Artificial Analysis | 31.4% | 17.4% |
| EnterpriseOps-Gym | Artificial Analysis | – | 47.3% |
| AA-Briefcase v1.1 | Artificial Analysis | 1678 | – |
| 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 | – | 43.0%† |
| LiveBench Mathematics | LiveBench | – | 91.2% |
| Arena Maths | Arena (LMArena) | – | 1491 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 60.3% |
| LiveBench 2.0 Data Analysis | LiveBench | 79.1% | 76.5%† |
| LiveBench Research | LiveBench | 77.9% | 67.7%† |
| LiveBench 1.0 Data Analysis | LiveBench | – | 76.5% |
| AA-Omniscience | Artificial Analysis | 29.5 | 27.2 |
| MMLU-Pro | Vals AI | – | 88.3% |
| LegalBench | Vals AI | – | 85.3% |
| CorpFin | Vals AI | – | 70.9% |
| TaxEval | Vals AI | – | 80.4% |
| BioMysteryBench | Vals AI | – | 64.8% |
| Excel Modeling Benchmark | Vals AI | – | 57.0% |
| MedCode | Vals AI | – | 49.4% |
| MedScribe | Vals AI | – | 90.1% |
| Public Benefits Bench v1.1 | Vals AI | – | 68.5% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 16.0% |
| AA-Omniscience: accuracy | Artificial Analysis | 51.0% | 45.4% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 56.1% | 66.7% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 78.6% |
| LiveBench Instruction Following | LiveBench | – | 74.3% |
| Arena Instruction Following | Arena (LMArena) | – | 1472 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1491 |
| Arena Creative Writing | Arena (LMArena) | – | 1439 |
| Arena Multi-turn | Arena (LMArena) | – | 1511 |
| Arena Longer Queries | Arena (LMArena) | – | 1488 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1304 |
| LiveBench Design | LiveBench | 77.8% | 67.1%† |
| MMMU-Pro | Artificial Analysis | 83.9% | – |
| MMMU-Pro (Vals) | Vals AI | – | 86.1% |
| MortgageTax | Vals AI | – | 65.4% |
| SAGE | Vals AI | – | 47.7% |
| Long context | |||
| AA-LCR | Artificial Analysis | 86.3% | 79.0% |
| MLCR | Artificial Analysis | – | 7.2% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 155.1† |
| LiveBench 2.0 | LiveBench | 76.7% | 62.4%† |
| LiveBench 1.0 | LiveBench | – | 78.0% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 55.1 | 39.6 |
| Vals Multimodal Index | Vals AI | – | 69.8%† |
| AA Cyber Index | Artificial Analysis | 64.1 | – |
Data as of 2026-10-24. Best configuration of each model; every score links to its source on the model pages.
What changed
- Kimi K3.1 Pro: BenchLeader Index 65.6 → 66.8.
- Kimi K3.1 Pro: 5 new results (FrontierCode 1.1 (AA), AA Cyber Index, CWE-Bench (AA)…).
- Kimi K3.1 Pro: first results.
- Muse Spark 1.2 (xhigh): 1 new result (Harvey's Legal Agent Benchmark v1).
- Muse Spark 1.2 (xhigh): 2 score revisions.
- Muse Spark 1.2 (xhigh): BenchLeader Index 62.6 → 63.3.
- Muse Spark 1.2 (xhigh): 4 new results (AutomationBench, GDP.pdf (AA), MLCR…).
- Muse Spark 1.2 (xhigh): 3 new results (Chess Puzzles, ProgramBench, SREBench); 1 score revision.
- Muse Spark 1.2 (xhigh): 3 score revisions.
- Muse Spark 1.2 (xhigh): 1 score revision.
Related comparisons
- Kimi K3.1 Pro vs Claude Opus 5.5
- Kimi K3.1 Pro vs Gemini 4 Argon
- Kimi K3.1 Pro vs Muse Wonder Full
- Muse Spark 1.2 vs Claude Opus 5.5
- Muse Spark 1.2 vs Gemini 4 Argon
- Muse Spark 1.2 vs Muse Wonder Full
- Muse Spark 1.2 vs Claude Fable 5.1
- Kimi K3 vs Muse Spark 1.2
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Kimi K3.1 Pro vs Muse Spark 1.2: questions
- Is Kimi K3.1 Pro better than Muse Spark 1.2?
- Kimi K3.1 Pro and Muse Spark 1.2 (xhigh) are neck and neck on quality (66.8 vs 63.2, within the ±7.8 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, Kimi K3.1 Pro or Muse Spark 1.2, 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 Kimi K3.1 Pro better than Muse Spark 1.2 for agents and tool use?
- Kimi K3.1 Pro scores higher in agentic tasks (67 vs 55 on the category index, where 50 is average).
- Which is better for long documents?
- Kimi K3.1 Pro scores higher on long-context benchmarks (68 vs 65). Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Muse Spark 1.2 (xhigh) answers first: 17.6 s against 27.7 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, Kimi K3.1 Pro or Muse Spark 1.2?
- Muse Spark 1.2 streams faster: 307 against 81 output tokens per second.
- Do independent benchmarks agree on Kimi K3.1 Pro vs Muse Spark 1.2?
- Across the 10 benchmarks both have, Kimi K3.1 Pro leads 9, Muse Spark 1.2 leads 1. Every overall index that rates both puts Kimi K3.1 Pro ahead.
- When was Kimi K3.1 Pro released?
- Kimi K3.1 Pro was released on 23 Oct 2026.