Kimi K3.1 Pro Together vs Muse Spark
Full profiles: Kimi K3.1 Pro Together (Moonshot AI) and Muse Spark (Meta): every benchmark, price and rank.
Updated · Data from 6 sources
As of 9 Nov 2026, Kimi K3.1 Pro Together and Muse Spark are neck and neck on quality (60.5 vs 64.2 on the BenchLeader Index, inside the ±4.0 margin). Kimi K3.1 Pro Together leads in every category we measure both in.
Key facts (as of 9 Nov 2026)
- Kimi K3.1 Pro Together scores 60.5 on the BenchLeader Index and Muse Spark scores 64.2 (BenchLeader, 9 Nov 2026).
- Of the 2 benchmarks both models have, Kimi K3.1 Pro Together leads 2 (BenchLeader, 9 Nov 2026).
Kimi K3.1 Pro Together benchmarks 
Muse Spark 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 |
|---|---|---|---|
| Maths | Kimi K3.1 Pro Together | 66 vs 59 category score; OTIS Mock AIME 100.0% vs 88.9% | Medium |
| Reasoning | Either | 67 vs 68 category score; GPQA Diamond 94.2% vs 89.8% | Either |
| Knowledge | Kimi K3.1 Pro Together | 68 vs 63 category score | Medium |
| Chat quality (human preference) | – | Only Muse Spark has an Arena rating (68 category score) | Not comparable |
| 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 Together (max) and Muse Spark are neck and neck on quality (60.5 vs 64.2, within the ±4.0 margin).
- Kimi K3.1 Pro Together (max) is stronger in knowledge, maths.
- Muse Spark is stronger in reasoning, agents & tools, coding, human preference, instruction following, long context, multimodal.
At a glance
| Spec | Kimi K3.1 Pro Together | Muse Spark |
|---|---|---|
| Developer | Moonshot AI | Meta |
| Released | 23 Oct 2026 | 8 Apr 2026 |
| Context window (tokens) | – | 262,144 |
| Compared at | Kimi K3.1 Pro Together (max) | Muse Spark |
| Open weights | No | No |
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 Together (max) | Muse Spark | Leader |
|---|---|---|---|
| Reasoning | 67.1 | 67.5 | level |
| Coding | – | 65.2 | not comparable |
| Agents & tools | – | 65.0 | not comparable |
| Maths | 65.8 | 59.2 | Kimi K3.1 Pro Together |
| Knowledge | 67.6 | 63.1 | Kimi K3.1 Pro Together |
| Instruction following | – | 76.9 | not comparable |
| Human preference | – | 68.2 | not comparable |
| Multimodal | – | 64.2 | not comparable |
| Long context | – | 63.6 | 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: Coding, Agents & tools, Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 2 benchmarks both have, Kimi K3.1 Pro Together leads 2, Muse Spark leads 0.
| Overall index | Kimi K3.1 Pro Together (max) | Muse Spark | Leader |
|---|---|---|---|
| BenchLeader Index | 60.5 | 64.2 | neck and neck |
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).
Every benchmark
58 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 Together (max) | Muse Spark |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 60.5 | 64.2 |
| Knowledge score | BenchLeader | 67.6 | 63.1 |
| Maths score | BenchLeader | 65.8 | 59.2 |
| Reasoning score | BenchLeader | 67.1 | 67.5 |
| Agents & tools score | BenchLeader | – | 65.0 |
| Coding score | BenchLeader | – | 65.2 |
| Human preference score | BenchLeader | – | 68.2 |
| Instruction following score | BenchLeader | – | 76.9 |
| Long context score | BenchLeader | – | 63.6 |
| Multimodal score | BenchLeader | – | 64.2 |
| Context window | BenchLeader | – | 262,144 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 94.2% | 89.8% |
| Humanity's Last Exam | Scale AI / CAIS | – | 40.6% |
| Arena Hard Prompts | Arena (LMArena) | – | 1506 |
| GPQA Diamond (AA) | Artificial Analysis | – | 88.4% |
| Humanity's Last Exam (AA) | Artificial Analysis | – | 40.7% |
| GPQA Diamond (Vals) | Vals AI | – | 89.7% |
| CritPt | Artificial Analysis | – | 11.3% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 45.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 42.0% | – |
| Coding | |||
| SciCode | SciCode | – | 51.5% |
| Arena Coding | Arena (LMArena) | – | 1529 |
| SWE-bench (Vals) | Vals AI | – | 74.4% |
| SWE-Bench Pro | Scale AI SEAL | – | 55.0% |
| Vibe Code Bench v1.1 | Vals AI | – | 19.7% |
| SWE-Bench Pro (private) | Scale AI SEAL | – | 55.0% |
| SWE Atlas: Codebase QnA | Scale AI SEAL | – | 24.2% |
| SWE Atlas: Test Writing | Scale AI SEAL | – | 31.1% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 62.2% |
| Design Arena Website | Design Arena | – | 1258 |
| Agents & tools | |||
| Terminal-Bench Hard | Artificial Analysis | – | 45.5% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 91.5% |
| MCP Atlas | Scale AI SEAL | – | 82.2% |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 59.5% |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 78.3% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 65.8% | – |
Show all 58 benchmarks
| Metric | Publisher | Kimi K3.1 Pro Together (max) | Muse Spark |
|---|---|---|---|
| Maths | |||
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | 88.9% |
| ProofBench | Vals AI | – | 17.0% |
| AIME (Vals) | Vals AI | – | 96.9% |
| Arena Maths | Arena (LMArena) | – | 1468 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 62.2% | – |
| MMLU-Pro | Vals AI | – | 87.3% |
| LegalBench | Vals AI | – | 84.2% |
| CorpFin | Vals AI | – | 65.1% |
| TaxEval | Vals AI | – | 77.7% |
| PRBench Finance | Scale AI SEAL | – | 52.4% |
| PRBench Legal | Scale AI SEAL | – | 52.3% |
| MultiNRC | Scale AI SEAL | – | 59.0% |
| CaseLaw v2 | Vals AI | – | 63.1% |
| MedCode | Vals AI | – | 51.3% |
| MedScribe | Vals AI | – | 85.9% |
| Instruction following | |||
| IFBench | Artificial Analysis | – | 75.9% |
| MultiChallenge | Scale AI SEAL | – | 75.5% |
| TutorBench | Scale AI SEAL | – | 68.5% |
| Arena Instruction Following | Arena (LMArena) | – | 1465 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1489 |
| Arena Creative Writing | Arena (LMArena) | – | 1464 |
| Arena Multi-turn | Arena (LMArena) | – | 1493 |
| Arena Longer Queries | Arena (LMArena) | – | 1475 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1306 |
| MMMU-Pro | Artificial Analysis | – | 80.5% |
| MMMU-Pro (official) | MMMU | – | 80.4%† |
| MMMU-Pro (Vals) | Vals AI | – | 87.4% |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | – | 78.0% |
| Arena Document | Arena (LMArena) | – | 1467 |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 153.1 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 31.3 |
| AA Progress Index v1 | Artificial Analysis | – | 289.1 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 20.2% |
Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.
What changed
- Muse Spark: BenchLeader Index 64.6 → 64.1.
- Kimi K3.1 Pro Together (max): first results.
- Muse Spark: 1 score revision.
- Muse Spark: 1 new result (AA Progress Index v1).
- Muse Spark: 1 new result (PRBench Legal).
- Muse Spark: 1 new result (SWE Atlas: Codebase QnA).
- Muse Spark: 2 new results (PRBench Legal, MultiNRC).
- Muse Spark: BenchLeader Index 65.1 → 64.6.
- Muse Spark: 1 new result (PRBench Finance).
Related comparisons
- Kimi K3.1 Pro Together vs Claude Fable 5.2
- Kimi K3.1 Pro Together vs Claude Opus 5.5
- Kimi K3.1 Pro Together vs Gemini 4 Carbon
- Muse Spark vs Claude Fable 5.2
- Muse Spark vs Claude Opus 5.5
- Muse Spark vs Gemini 4 Carbon
- Muse Spark vs GPT-6 Astra
- Kimi K3 vs Muse Spark
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Kimi K3.1 Pro Together vs Muse Spark: questions
- Is Kimi K3.1 Pro Together better than Muse Spark?
- Kimi K3.1 Pro Together (max) and Muse Spark are neck and neck on quality (60.5 vs 64.2, within the ±4.0 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
- Do independent benchmarks agree on Kimi K3.1 Pro Together vs Muse Spark?
- Across the 2 benchmarks both have, Kimi K3.1 Pro Together leads 2, Muse Spark leads 0.
- When was Kimi K3.1 Pro Together released?
- Kimi K3.1 Pro Together was released on 23 Oct 2026.