Muse Spark Open vs Nova 2.0 Pro Preview
Full profiles: Muse Spark Open (Meta) and Nova 2.0 Pro Preview (Amazon): every benchmark, price and rank.
Updated · Data from 10 sources
As of 16 Nov 2026, Muse Spark Open and Nova 2.0 Pro Preview are neck and neck on quality (53.5 vs 53.4 on the BenchLeader Index, inside the ±12.2 margin), and Muse Spark Open is 1.7× cheaper at $2.00 vs $3.44 per 1M tokens blended. Choose Muse Spark Open for multimodal (63 vs 47) and long context (64 vs 56) and fast first answers (9.9 s vs 16.1 s), where it also streams ~1.5× faster; choose Nova 2.0 Pro Preview for coding (43 vs 36).
Key facts (as of 16 Nov 2026)
- Muse Spark Open scores 53.5 on the BenchLeader Index and Nova 2.0 Pro Preview scores 53.4 (BenchLeader, 16 Nov 2026).
- Muse Spark Open costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
- Nova 2.0 Pro Preview costs $3.44 per 1M tokens blended (list price, 16 Nov 2026).
- Muse Spark Open streams ~1.5× faster than Nova 2.0 Pro Preview (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 9 benchmarks both models have, Muse Spark Open leads 9 (BenchLeader, 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 | Nova 2.0 Pro Preview | 43 vs 36 category score; Terminal-Bench 2.1 (AA) 29.6% vs 76.4% | Medium |
| Long documents | Muse Spark Open | 64 vs 56 category score; AA-LCR v1.1 78.3% vs 64.0% | High |
| Images and other media | Muse Spark Open | 63 vs 47 category score; MMMU-Pro 80.9% vs 64.5% | High |
| Lowest cost | Muse Spark Open | $2.00 vs $3.44 per 1M blended; agentic coding session $0.092 vs $0.115 | – |
| Fastest first answer | Muse Spark Open | 9.9 s (Muse Spark Open (xhigh)) vs 16.1 s (Nova 2.0 Pro Preview (medium)) 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 Open (xhigh) and Nova 2.0 Pro Preview (medium) are neck and neck on quality (53.5 vs 53.4, within the ±12.2 margin).
- Muse Spark Open (xhigh) is stronger in long context, multimodal.
- Nova 2.0 Pro Preview (medium) is stronger in coding.
- Muse Spark Open (xhigh) is 1.7× cheaper ($2.00 vs $3.44 per 1M blended).
- Muse Spark Open (xhigh) streams 1.8× faster (180 vs 98 tokens per second).
At a glance
| Spec | Muse Spark Open | Nova 2.0 Pro Preview |
|---|---|---|
| Developer | Meta | Amazon |
| Released | 15 Oct 2026 | 2 Dec 2025 |
| Context window (tokens) | 1,048,576 | 256,000 |
| Compared at | Muse Spark Open (xhigh) | Nova 2.0 Pro Preview (medium) |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $1.25 / $4.25 / $0.150 | $1.25 / $10.00 / – |
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 Open (xhigh) | Nova 2.0 Pro Preview (medium) | Leader |
|---|---|---|---|
| Reasoning | 51.3 | – | not comparable |
| Coding | 36.0 | 43.1 | Nova 2.0 Pro Preview |
| Agents & tools | – | 54.8 | not comparable |
| Knowledge | 58.8 | – | not comparable |
| Instruction following | – | 76.8 | not comparable |
| Multimodal | 63.3 | 46.5 | Muse Spark Open |
| Long context | 63.8 | 56.3 | Muse Spark Open |
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: Reasoning, Agents & tools, Maths, Knowledge, Instruction following, Human preference.
Where sources disagree
Across the 9 benchmarks both have, Muse Spark Open leads 9, Nova 2.0 Pro Preview leads 0.
| Overall index | Muse Spark Open (xhigh) | Nova 2.0 Pro Preview (medium) | Leader |
|---|---|---|---|
| BenchLeader Index | 53.5 | 53.4 | 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).
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 Open (xhigh) | Nova 2.0 Pro Preview (medium) |
|---|---|---|
| Blended price per 1M tokens | $2.00 | $3.44 |
| Input / output per 1M | $1.25 / $4.25 | $1.25 / $10.00 |
| Cached input per 1M | $0.150 | – |
| Price per task: chat reply | $0.0018 | $0.0035 |
| Price per task: summarize a 30-page report | $0.018 | $0.021 |
| Price per task: code edit | $0.014 | $0.022 |
| Price per task: agentic coding session | $0.092 | $0.115 |
| Price per task: structured extraction | $0.0034 | $0.0045 |
| Agentic coding session, input mostly cached | $0.043 | – |
| Cost per benchmark task (AA Index) | $2.02 | – |
| Output tokens per task (AA Index) | 66k | – |
| Of which reasoning | 32k | – |
| Time per task (AA Index) | 6 min | – |
| Output speed | 180 tok/s | 98 tok/s |
| Time to first answer | 9.9 s | 16.1 s |
| Time to a complete answer, last measured 13 Nov 2026 | 39.9 s | 32.3 s |
Each model is compared at its best-ranked reasoning-effort setting. Muse Spark Open (xhigh) scores 53.5 and takes 10 s to its first answer token. Nova 2.0 Pro Preview (medium) scores 53.4 and takes 16 s to its first answer token; Nova 2.0 Pro Preview (low) scores 51.9 in 7 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
82 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 Open (xhigh) | Nova 2.0 Pro Preview (medium) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 53.5 | 53.4 |
| Coding score | BenchLeader | 36.0 | 43.1 |
| Knowledge score | BenchLeader | 58.8 | – |
| Long context score | BenchLeader | 63.8 | 56.3 |
| Multimodal score | BenchLeader | 63.3 | 46.5 |
| Reasoning score | BenchLeader | 51.3 | – |
| Agents & tools score | BenchLeader | – | 54.8 |
| Instruction following score | BenchLeader | – | 76.8 |
| Blended price $/M | BenchLeader | $2.00 | $3.44 |
| Output speed | BenchLeader | 180 tok/s | 98 tok/s |
| Time to first answer | BenchLeader | 9.9 s | 16.1 s |
| Context window | BenchLeader | 1,048,576 tokens | 256,000 tokens |
| Reasoning | |||
| LiveBench 2.0 Reasoning | LiveBench | 73.7%† | – |
| GPQA Diamond (AA) | Artificial Analysis | 89.0% | 78.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 43.9% | 9.4% |
| HLE-Diamond (AA) | Artificial Analysis | 26.3% | – |
| ARC-AGI-1 | ARC Prize | 89.0% | – |
| ARC-AGI-2 | ARC Prize | 57.5% | – |
| ARC-AGI-3 | ARC Prize | 0.4% | – |
| CritPt | Artificial Analysis | 14.9% | 0.0% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 29.5% | – |
| HLE-Diamond (Scale) | Scale AI SEAL | 28.0%† | – |
| Coding | |||
| SciCode | SciCode | – | 42.7% |
| Arena WebDev | Arena (LMArena) | 1526† | – |
| LiveBench 2.0 Coding | LiveBench | 55.1%† | – |
| SciCode (AA) | Artificial Analysis | 58.5% | – |
| Code Migration | Vals AI | 21.2% | – |
| Code Migration v1.1 | Vals AI | 26.9% | – |
| Vibe Code Bench v1.1 | Vals AI | 76.2% | – |
| SWE Atlas v1.1 | Scale AI SEAL | 42.3%† | – |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | 50.0%† | – |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | 41.1%† | – |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | 35.7%† | – |
| SWE-Bench Pro V2 | Scale AI SEAL | 95.0% | – |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | 82.3% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 8.1% | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 76.4% | 29.6% |
Show all 82 benchmarks
| Metric | Publisher | Muse Spark Open (xhigh) | Nova 2.0 Pro Preview (medium) |
|---|---|---|---|
| Coding | |||
| GameBench 2 Overall | DuelLab GameBench 2 | 55.3† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 59.3 | – |
| Design Arena Website | Design Arena | 1305 | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 27.6% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 7.6% | – |
| LiveCodeBench (AA) | Artificial Analysis | – | 73.0% |
| Agents & tools | |||
| LiveBench Long Agentic | LiveBench | 12.1%† | – |
| LiveBench Browser | LiveBench | 26.2%† | – |
| Terminal-Bench Hard | Artificial Analysis | – | 24.2% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 92.7% |
| HiL-Bench | Scale AI SEAL | 59.7%† | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 45.1% | 0.0% |
| GDPval-AA v2.1 | Artificial Analysis | 1401 | 477 |
| Finance Agent v2 | Vals AI | 61.3% | – |
| Finance Agent v2.1 | Vals AI | 60.7% | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 25.0% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 16.7% | – |
| Legal Research Bench | Vals AI | 38.5% | – |
| Tax Agent Bench | Vals AI | 26.3% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 6.6% | – |
| AutomationBench | Artificial Analysis | 49.7% | – |
| GDP.pdf (AA) | Artificial Analysis | 18.6% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1280 | – |
| GDPx | GDPx by SemiAnalysis | 1.7%† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 1.9% | – |
| Maths | |||
| ArXivMath | MathArena | 27.0% | – |
| BrokenArXiv | MathArena | 30.1% | – |
| AIME 2025 (AA) | Artificial Analysis | – | 89.0% |
| Knowledge | |||
| LiveBench 2.0 Data Analysis | LiveBench | 60.2%† | – |
| LiveBench Research | LiveBench | 82.7%† | – |
| AA-Omniscience v1.1 | Artificial Analysis | 25.8 | – |
| PRBench Legal | Scale AI SEAL | 59.8%† | – |
| Excel Modeling Benchmark | Vals AI | 53.7% | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 62.0% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 2.0%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 42.0% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 72.0% | – |
| Global-MMLU-Lite (AA) | Artificial Analysis | – | 87.6%† |
| Instruction following | |||
| IFBench | Artificial Analysis | – | 79.0% |
| MultiChallenge | Scale AI SEAL | 74.2%† | – |
| Multimodal | |||
| LiveBench Design | LiveBench | 58.1%† | – |
| MMMU-Pro | Artificial Analysis | 80.9% | 64.5% |
| SAGE | Vals AI | 85.8% | – |
| Humanity's Sixth Sense | Scale AI SEAL | 29.6%† | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 78.3% | 64.0% |
| MLCR | Artificial Analysis | 7.8% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 155.4† | – |
| LiveBench 2.0 | LiveBench | 48.5%† | – |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 24.9 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 38.9 | 14.2 |
| AA Progress Index v1 | Artificial Analysis | 306.7 | 244.3 |
| Vals Index | Vals AI | 48.6 | – |
| Vals Finance Index | Vals AI | 53.0% | – |
| Vals Legal Index | Vals AI | 68.5% | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 7.6%† | – |
| DistressBench | Scale AI SEAL | 87.7%† | – |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 27.8 | – |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Muse Spark Open (xhigh): 1 score revision.
- Muse Spark Open (xhigh): 1 new result (GameBench 2 by reasoning setting); 1 score revision.
- Muse Spark Open (xhigh): BenchLeader Index 53.3 → 53.8.
- Muse Spark Open (xhigh): 1 new result (ARC-AGI-3).
- Muse Spark Open (xhigh): BenchLeader Index 59.5 → 53.3.
- Nova 2.0 Pro Preview (medium): BenchLeader Index 52.4 → 53.6.
- Muse Spark Open (xhigh): 6 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $0.84/M to $2.02/M (139% up).
- Nova 2.0 Pro Preview (medium): 1 new result (AA Progress Index v1).
- Muse Spark Open (xhigh): 6 new results (MLCR, Code Migration v1.1, Excel Modeling Benchmark v1.1…); cached input price moved from $1.25/M to $0.15/M (88% down).
- Muse Spark Open (xhigh): 6 new results (FrontierCode 1.1 (AA), Terminal-Bench-Science 0.1 (AA), Vals Index…).
Related comparisons
- Muse Spark Open vs Claude Opus 5.5
- Muse Spark Open vs GPT-6 Astra
- Muse Spark Open vs GPT-6.1 Sol
- Muse Spark Open vs Claude Fable 5
- Muse Spark Open vs Gemini 4 Argon
- Muse Spark Open vs GPT-5.6 Sol
- Muse Spark Open vs Claude Sonnet 5.5
- Muse Spark Open vs Claude Opus 4.7
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Muse Spark Open vs Nova 2.0 Pro Preview: questions
- Is Muse Spark Open better than Nova 2.0 Pro Preview?
- Muse Spark Open (xhigh) and Nova 2.0 Pro Preview (medium) are neck and neck on quality (53.5 vs 53.4, within the ±12.2 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 Open vs Nova 2.0 Pro Preview: which is cheaper, and will that change?
- Muse Spark Open is cheaper today: $2.00 against $3.44 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Muse Spark Open or Nova 2.0 Pro Preview better for coding?
- Nova 2.0 Pro Preview scores higher in coding (43 vs 36 on the category index, where 50 is average).
- Which is faster, Muse Spark Open or Nova 2.0 Pro Preview?
- Muse Spark Open streams ~1.5× faster (180 vs 98 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Muse Spark Open scores higher on long-context benchmarks (64 vs 56). Muse Spark Open accepts more context: 1,048,576 against 256,000 tokens for Nova 2.0 Pro Preview.
More questions (3)
- Which has lower latency?
- Muse Spark Open answers first: 9.9 s against 16.1 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 Open vs Nova 2.0 Pro Preview?
- Across the 9 benchmarks both have, Muse Spark Open leads 9, Nova 2.0 Pro Preview leads 0.
- When was Muse Spark Open released?
- Muse Spark Open was released on 15 Oct 2026.