Muse Spark vs Muse Spark 1.2
Full profiles: Muse Spark (Meta) and Muse Spark 1.2 (Meta): every benchmark, price and rank.
Updated · Data from 8 sources
As of 25 Oct 2026, Muse Spark and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.3 vs 63.2, inside the ±5.5 margin of error) and close on price, so pick on the category that matters to you. Pick Muse Spark for agents & tools (66 vs 55); pick Muse Spark 1.2 for maths (67 vs 59).
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 |
|---|---|---|---|
| Coding | Muse Spark | 65 vs 55 category score; SciCode 51.5% vs 57.4% | High |
| Agents & tool use | Muse Spark | 66 vs 55 category score | High |
| Maths | Muse Spark 1.2 | 67 vs 59 category score; Arena Maths 1491 vs 1467 | High |
| Reasoning | Muse Spark 1.2 | 69 vs 65 category score; CritPt 17.7% vs 11.3% | Medium |
| Knowledge | Muse Spark 1.2 | 67 vs 63 category score; AA-Omniscience 27.2 vs 7.2 | Medium |
| Long documents | Either | 64 vs 65 category score; AA-LCR 78.0% vs 79.0% | Either |
| Images and other media | Either | 65 vs 65 category score; Arena Vision 1306 vs 1304 | Either |
| Chat quality (human preference) | Either | 68 vs 69 on Arena votes | Either |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Muse Spark and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.3 vs 63.2, within the ±5.5 margin).
- Muse Spark is stronger in agents & tools, coding, instruction following.
- Muse Spark 1.2 (xhigh) is stronger in composite, human preference, knowledge, long context, maths, multimodal, reasoning.
At a glance
| Spec | Muse Spark | Muse Spark 1.2 |
|---|---|---|
| Developer | Meta | Meta |
| Released | 8 Apr 2026 | 5 Aug 2026 |
| Context window (tokens) | 262,144 | 1,048,576 |
| Compared at | Muse Spark | Muse Spark 1.2 (xhigh) |
| Open weights | No | No |
| Price in / out / cached input per 1M | – | $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 | Muse Spark | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 65.3 | 69.3 | Muse Spark 1.2 |
| Coding | 65.0 | 55.1 | Muse Spark |
| Agents & tools | 66.1 | 55.4 | Muse Spark |
| Maths | 59.1 | 67.3 | Muse Spark 1.2 |
| Knowledge | 63.3 | 66.7 | Muse Spark 1.2 |
| Instruction following | 77.3 | – | not comparable |
| Human preference | 68.3 | 68.6 | level |
| Multimodal | 64.5 | 65.2 | level |
| Long context | 64.0 | 64.5 | level |
| Composite | 64.5 | 73.8 | Muse Spark 1.2 |
Where sources disagree
Across the 26 benchmarks both have, Muse Spark leads 5, Muse Spark 1.2 leads 21. Every overall index that rates both puts Muse Spark 1.2 ahead.
| Overall index | Muse Spark | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| BenchLeader Index | 64.3 | 63.2 | neck and neck |
| AA Intelligence Index v4.3.2 | 31.3 | 39.6 | Muse Spark 1.2 |
| Arena Text | 1489 | 1491 | 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; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | Muse Spark | Muse Spark 1.2 (xhigh) |
|---|---|---|
| Blended price per 1M tokens | – | $2.00 |
| Input / output per 1M | – / – | $1.25 / $4.25 |
| Cached input per 1M | – | $0.150 |
| Price per task: chat reply | – | $0.0018 |
| Price per task: summarize a 30-page report | – | $0.018 |
| Price per task: code edit | – | $0.014 |
| Price per task: agentic coding session | – | $0.092 |
| Price per task: structured extraction | – | $0.0034 |
| Cost to run a full benchmark suite | – | $0.975 |
| Output speed | – | 307 tok/s |
| Time to first answer | – | 17.6 s |
| Time to a complete answer | – | 19.2 s |
Each model is compared at its best-ranked reasoning-effort setting. Muse Spark scores 64.3. 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
109 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 | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.3 | 63.2 |
| Agents & tools score | BenchLeader | 66.1 | 55.4 |
| Coding score | BenchLeader | 65.0 | 55.1 |
| Composite score | BenchLeader | 64.5 | 73.8 |
| Human preference score | BenchLeader | 68.3 | 68.6 |
| Instruction following score | BenchLeader | 77.3 | – |
| Knowledge score | BenchLeader | 63.3 | 66.7 |
| Long context score | BenchLeader | 64.0 | 64.5 |
| Maths score | BenchLeader | 59.1 | 67.3 |
| Multimodal score | BenchLeader | 64.5 | 65.2 |
| Reasoning score | BenchLeader | 65.3 | 69.3 |
| Blended price $/M | BenchLeader | – | $2.00 |
| Output speed | BenchLeader | – | 307 tok/s |
| Time to first answer | BenchLeader | – | 17.6 s |
| Context window | BenchLeader | 262,144 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 89.8% | – |
| Humanity's Last Exam | Scale AI / CAIS | 40.6% | – |
| SimpleBench | SimpleBench | – | 74.5%† |
| Arena Hard Prompts | Arena (LMArena) | 1506 | 1512 |
| LiveBench 2.0 Reasoning | LiveBench | – | 90.0%† |
| LiveBench 1.0 Reasoning | LiveBench | – | 90.0% |
| GPQA Diamond (AA) | Artificial Analysis | 88.4% | 90.4% |
| Humanity's Last Exam (AA) | Artificial Analysis | 40.7% | 45.5% |
| GPQA Diamond (Vals) | Vals AI | 89.7% | – |
| CritPt | Artificial Analysis | 11.3% | 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 | 51.5% | 57.4% |
| WeirdML | WeirdML | – | 60.3% |
| Arena Coding | Arena (LMArena) | 1529 | 1541 |
| Arena WebDev | Arena (LMArena) | – | 1533 |
| LiveBench 2.0 Coding | LiveBench | – | 78.2%† |
| LiveBench 1.0 Coding | LiveBench | – | 77.5% |
| SciCode (AA) | Artificial Analysis | – | 57.4% |
| IOI | Vals AI | – | 21.8% |
| SWE-bench (Vals) | Vals AI | 74.4% | 86.6% |
| SWE-Bench Pro | Scale AI SEAL | 55.0% | – |
| Code Migration | Vals AI | – | 29.9% |
| ProgramBench | Vals AI | – | 0.5% |
Show all 109 benchmarks
| Metric | Publisher | Muse Spark | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| Coding | |||
| Vibe Code Bench v1.1 | Vals AI | 19.7% | 79.1% |
| 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% | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 54.9% |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 12.0% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 7.1% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 62.2% | 80.2% |
| Startrise Frontend | Startrise | – | 70.3%† |
| Agents & tools | |||
| APEX-Agents | Mercor | – | 45.4%† |
| Arena Agent | Arena (LMArena) | – | -7 |
| LiveBench Long Agentic | LiveBench | – | 21.3%† |
| LiveBench Browser | LiveBench | – | 36.0%† |
| LiveBench Agentic Coding | LiveBench | – | 57.6% |
| Terminal-Bench Hard | Artificial Analysis | 45.5% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 91.5% | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 69.7% |
| MCP Atlas | Scale AI SEAL | 82.2% | – |
| 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 2.0 (Vals) | Vals AI | 59.5% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 6.1% |
| AutomationBench | Artificial Analysis | – | 40.6% |
| GDP.pdf (AA) | Artificial Analysis | – | 17.4% |
| EnterpriseOps-Gym | Artificial Analysis | – | 47.3% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1327 |
| Maths | |||
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 88.9% | – |
| ProofBench | Vals AI | 17.0% | 43.0%† |
| LiveBench Mathematics | LiveBench | – | 91.2% |
| AIME (Vals) | Vals AI | 96.9% | – |
| Arena Maths | Arena (LMArena) | 1467 | 1491 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 60.3% |
| LiveBench 2.0 Data Analysis | LiveBench | – | 76.5%† |
| LiveBench Research | LiveBench | – | 67.7%† |
| LiveBench 1.0 Data Analysis | LiveBench | – | 76.5% |
| AA-Omniscience | Artificial Analysis | 7.2 | 27.2 |
| MMLU-Pro | Vals AI | 87.3% | 88.3% |
| LegalBench | Vals AI | 84.2% | 85.3% |
| CorpFin | Vals AI | 65.1% | 70.9% |
| TaxEval | Vals AI | 77.7% | 80.4% |
| PRBench Finance | Scale AI SEAL | 52.4% | – |
| PRBench Legal | Scale AI SEAL | 52.3% | – |
| MultiNRC | Scale AI SEAL | 59.0% | – |
| BioMysteryBench | Vals AI | – | 64.8% |
| CaseLaw v2 | Vals AI | 63.1% | – |
| Excel Modeling Benchmark | Vals AI | – | 57.0% |
| MedCode | Vals AI | 51.3% | 49.4% |
| MedScribe | Vals AI | 85.9% | 90.1% |
| Public Benefits Bench v1.1 | Vals AI | – | 68.5% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 16.0% |
| AA-Omniscience: accuracy | Artificial Analysis | 49.6% | 45.4% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 15.8% | 66.7% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 78.6% |
| LiveBench Instruction Following | LiveBench | – | 74.3% |
| IFBench | Artificial Analysis | 75.9% | – |
| MultiChallenge | Scale AI SEAL | 75.5% | – |
| TutorBench | Scale AI SEAL | 68.5% | – |
| Arena Instruction Following | Arena (LMArena) | 1465 | 1472 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1489 | 1491 |
| Arena Creative Writing | Arena (LMArena) | 1464 | 1439 |
| Arena Multi-turn | Arena (LMArena) | 1494 | 1511 |
| Arena Longer Queries | Arena (LMArena) | 1476 | 1488 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1306 | 1304 |
| LiveBench Design | LiveBench | – | 67.1%† |
| MMMU-Pro | Artificial Analysis | 80.5% | – |
| MMMU-Pro (official) | MMMU | 80.4%† | – |
| MMMU-Pro (Vals) | Vals AI | 87.4% | 86.1% |
| MortgageTax | Vals AI | – | 65.4% |
| SAGE | Vals AI | – | 47.7% |
| Long context | |||
| AA-LCR | Artificial Analysis | 78.0% | 79.0% |
| Arena Document | Arena (LMArena) | 1467 | – |
| MLCR | Artificial Analysis | – | 7.2% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 152.0 | 155.1† |
| LiveBench 2.0 | LiveBench | – | 62.4%† |
| LiveBench 1.0 | LiveBench | – | 78.0% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 31.3 | 39.6 |
| Vals Multimodal Index | Vals AI | – | 69.8%† |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 20.2% | – |
Data as of 2026-10-25. Best configuration of each model; every score links to its source on the model pages.
What changed
- Muse Spark 1.2 (xhigh): 1 new result (AA-Briefcase v1.1).
- 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 new result (PRBench Legal).
- Muse Spark 1.2 (xhigh): 1 score revision.
- Muse Spark: 1 new result (SWE Atlas: Codebase QnA).
Related comparisons
- Muse Spark vs Claude Opus 5.5
- Muse Spark vs Gemini 4 Argon
- Muse Spark 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
- Muse Spark vs Muse Spark 1.1
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Muse Spark vs Muse Spark 1.2: questions
- Is Muse Spark better than Muse Spark 1.2?
- Muse Spark and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.3 vs 63.2, within the ±5.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-25, so check the category scores for your use.
- Is Muse Spark better than Muse Spark 1.2 for coding?
- Muse Spark scores higher in coding (65 vs 55 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 51.5% for Muse Spark against 57.4% for Muse Spark 1.2.
- Is Muse Spark better than Muse Spark 1.2 for agents and tool use?
- Muse Spark scores higher in agentic tasks (66 vs 55 on the category index, where 50 is average).
- Which is better for long documents?
- They are level on long-context benchmarks (64 vs 65). Muse Spark 1.2 accepts more context: 1,048,576 against 262,144 tokens for Muse Spark.
- Do independent benchmarks agree on Muse Spark vs Muse Spark 1.2?
- Across the 26 benchmarks both have, Muse Spark leads 5, Muse Spark 1.2 leads 21. Every overall index that rates both puts Muse Spark 1.2 ahead.
- When was Muse Spark 1.2 released?
- Muse Spark 1.2 was released on 5 Aug 2026.