GPT-5.5 vs Muse Spark 1.2
Full profiles: GPT-5.5 (OpenAI) and Muse Spark 1.2 (Meta): every benchmark, price and rank.
Updated · Data from 13 sources
As of 10 Nov 2026, GPT-5.5 and Muse Spark 1.2 are neck and neck on quality (64.2 vs 61.7 on the BenchLeader Index, inside the ±6.3 margin), and Muse Spark 1.2 is 5.6× cheaper at $2.00 vs $11.25 per 1M tokens blended. Choose GPT-5.5 for agents & tools (62 vs 56), coding (61 vs 55), and long context (67 vs 64); choose Muse Spark 1.2 for fast first answers (7.9 s vs 28.6 s) and multimodal (65 vs 62) and knowledge (65 vs 64), where it also streams ~2× faster.
Key facts (as of 10 Nov 2026)
- GPT-5.5 scores 64.2 on the BenchLeader Index and Muse Spark 1.2 scores 61.7 (BenchLeader, 10 Nov 2026).
- GPT-5.5 costs $11.25 per 1M tokens blended (list price, 10 Nov 2026).
- Muse Spark 1.2 costs $2.00 per 1M tokens blended (list price, 10 Nov 2026).
- Muse Spark 1.2 streams ~2× faster than GPT-5.5 (Artificial Analysis, 7-day median, 10 Nov 2026).
- Of the 51 benchmarks both models have, GPT-5.5 leads 31 (BenchLeader, 10 Nov 2026).
- On Arena WebDev, GPT-5.5 is rated 1512 and Muse Spark 1.2 1534 (LMArena, as published by 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 | GPT-5.5 | 61 vs 55 category score; WeirdML 84.9% vs 60.3% | Medium |
| Agents & tool use | GPT-5.5 | 62 vs 56 category score; τ³-Banking (AA) 39.0% vs 34.9% | Medium |
| Maths | GPT-5.5 | 70 vs 67 category score; LiveBench Mathematics 95.9% vs 91.2% | Medium |
| Reasoning | Either | 68 vs 68 category score; LiveBench 1.0 Reasoning 89.7% vs 90.0% | Either |
| Knowledge | Muse Spark 1.2 | 65 vs 64 category score; MMLU-Pro 88.3% vs 88.1% | Medium |
| Long documents | GPT-5.5 | 67 vs 64 category score; AA-LCR v1.1 84.3% vs 79.0% | Medium |
| Images and other media | Muse Spark 1.2 | 65 vs 62 category score; MMMU-Pro (Vals) 86.1% vs 88.3% | 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 $11.25 per 1M blended; agentic coding session $0.092 vs $0.420 | – |
| Fastest first answer | Muse Spark 1.2 | 7.9 s (Muse Spark 1.2 (xhigh)) vs 28.6 s (GPT-5.5 (xhigh)) 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
- GPT-5.5 (xhigh) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.2 vs 61.7, within the ±6.3 margin).
- GPT-5.5 (xhigh) is stronger in agents & tools, coding, instruction following, long context, maths.
- Muse Spark 1.2 (xhigh) is stronger in knowledge, multimodal, human preference.
- Muse Spark 1.2 (xhigh) is 5.6× cheaper ($2.00 vs $11.25 per 1M blended).
- Muse Spark 1.2 (xhigh) streams 2.4× faster (192 vs 79 tokens per second).
At a glance
| Spec | GPT-5.5 | Muse Spark 1.2 |
|---|---|---|
| Developer | OpenAI | Meta |
| Released | 23 Apr 2026 | 5 Aug 2026 |
| Context window (tokens) | 1,050,000 | 1,048,576 |
| Compared at | GPT-5.5 (xhigh) | Muse Spark 1.2 (xhigh) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $5.00 / $30.00 / $0.500 | $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 | GPT-5.5 (xhigh) | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 68.3 | 68.3 | level |
| Coding | 60.9 | 55.0 | GPT-5.5 |
| Agents & tools | 61.8 | 55.5 | GPT-5.5 |
| Maths | 69.6 | 67.2 | GPT-5.5 |
| Knowledge | 63.7 | 64.7 | Muse Spark 1.2 |
| Instruction following | 74.0 | – | not comparable |
| Human preference | – | 68.7 | not comparable |
| Multimodal | 62.3 | 65.3 | Muse Spark 1.2 |
| Long context | 67.0 | 64.2 | GPT-5.5 |
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, Human preference.
Where sources disagree
Across the 51 benchmarks both have, GPT-5.5 leads 31, Muse Spark 1.2 leads 19 and 1 is a tie. Every overall index that rates both puts Muse Spark 1.2 ahead.
| Overall index | GPT-5.5 (xhigh) | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| BenchLeader Index | 64.2 | 61.7 | neck and neck |
| Arena Text | 1481† | 1494 | 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | GPT-5.5 (xhigh) | Muse Spark 1.2 (xhigh) |
|---|---|---|
| Blended price per 1M tokens | $11.25 | $2.00 |
| Input / output per 1M | $5.00 / $30.00 | $1.25 / $4.25 |
| Cached input per 1M | $0.500 | $0.150 |
| Price per task: chat reply | $0.011 | $0.0018 |
| Price per task: summarize a 30-page report | $0.078 | $0.018 |
| Price per task: code edit | $0.075 | $0.014 |
| Price per task: agentic coding session | $0.420 | $0.092 |
| Price per task: structured extraction | $0.016 | $0.0034 |
| Agentic coding session, input mostly cached | $0.217 | $0.043 |
| Output speed | 79 tok/s | 192 tok/s |
| Time to first answer | 28.6 s | 7.9 s |
| Time to a complete answer | 75.1 s | 26.6 s |
Each model is compared at its best-ranked reasoning-effort setting. GPT-5.5 (xhigh) scores 64.2 and takes 29 s to its first answer token; GPT-5.5 (high) scores 63.7 in 18 s, GPT-5.5 scores 61.7 in 2 s. Muse Spark 1.2 (xhigh) scores 61.7 and takes 8 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
134 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 | GPT-5.5 (xhigh) | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.2 | 61.7 |
| Agents & tools score | BenchLeader | 61.8 | 55.5 |
| Coding score | BenchLeader | 60.9 | 55.0 |
| Instruction following score | BenchLeader | 74.0 | – |
| Knowledge score | BenchLeader | 63.7 | 64.7 |
| Long context score | BenchLeader | 67.0 | 64.2 |
| Maths score | BenchLeader | 69.6 | 67.2 |
| Multimodal score | BenchLeader | 62.3 | 65.3 |
| Reasoning score | BenchLeader | 68.3 | 68.3 |
| Human preference score | BenchLeader | – | 68.7 |
| Blended price $/M | BenchLeader | $11.25 | $2.00 |
| Output speed | BenchLeader | 79 tok/s | 192 tok/s |
| Time to first answer | BenchLeader | 28.6 s | 7.9 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 90.7%† | – |
| SimpleBench | SimpleBench | 69.0%† | 74.5%† |
| Arena Hard Prompts | Arena (LMArena) | 1499† | 1515 |
| LiveBench 1.0 Reasoning | LiveBench | 89.7% | 90.0% |
| GPQA Diamond (AA) | Artificial Analysis | 93.5% | 90.4% |
| Humanity's Last Exam (AA) | Artificial Analysis | 45.8% | 45.5% |
| GPQA Diamond (Vals) | Vals AI | 93.2% | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 88.8%† | – |
| ARC-AGI-1 | ARC Prize | 95.0% | – |
| ARC-AGI-2 | ARC Prize | 85.0% | – |
| ARC-AGI-3 | ARC Prize | 0.4%† | – |
| CritPt | Artificial Analysis | 27.1% | 17.7% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 63.0% | 27.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 56.0% | – |
| CL-bench Life | Epoch AI Benchmarking Hub | 22.2%† | – |
| LMCA | Epoch AI Benchmarking Hub | 54.3% | 48.4% |
| DTBench | Epoch AI Benchmarking Hub | 96.0% | 94.7% |
| ForecastBench | ForecastBench | 64.2%† | – |
| BTF-3 | Epoch AI Benchmarking Hub | 14.3%† | – |
| Coding | |||
| SciCode | SciCode | 55.8% | 57.4% |
| WeirdML | WeirdML | 84.9% | 60.3% |
| FrontierCode | Cognition | 43.0%† | – |
| GSO-Bench | GSO-Bench | 40.2% | – |
| Arena Coding | Arena (LMArena) | 1510† | 1543 |
| Arena WebDev | Arena (LMArena) | 1512 | 1534 |
Show all 134 benchmarks
| Metric | Publisher | GPT-5.5 (xhigh) | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| Coding | |||
| LiveBench 1.0 Coding | LiveBench | 82.2% | 77.5% |
| LiveCodeBench | Vals AI | 85.3% | – |
| IOI | Vals AI | – | 21.8% |
| SWE-bench (Vals) | Vals AI | 82.6% | 86.6% |
| Code Migration | Vals AI | 45.2% | 29.9% |
| ProgramBench | Vals AI | 0.5% | 0.5% |
| Vibe Code Bench v1.1 | Vals AI | 69.8% | 79.1% |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 45.4% | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 44.8% | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 42.6% | – |
| MirrorCode | Epoch AI Benchmarking Hub | 10.0%† | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 88.1%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 67.0% | 54.9% |
| ALE-Bench | Epoch AI Benchmarking Hub | 1943.0 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 12.0% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 14.7% | 7.1% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 84.3% | 80.2% |
| Startrise Frontend | Startrise | – | 70.3%† |
| GameBench 2 Overall | DuelLab GameBench 2 | 49.0† | 51.7† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 59.7 | 57.4 |
| Design Arena Website | Design Arena | 1252† | 1310† |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 84.7%† | – |
| OSWorld-Verified 2.0 | OSWorld | 13.0% | – |
| Remote Labor Index | Scale AI / CAIS | 6.3%† | – |
| APEX-Agents | Mercor | 55.1%† | 45.4%† |
| Arena Agent | Arena (LMArena) | – | -8 |
| LiveBench Agentic Coding | LiveBench | 54.0% | 57.6% |
| Terminal-Bench Hard | Artificial Analysis | 60.6% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 93.9% | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | 76.4%† | 69.7% |
| MCP Atlas | Scale AI SEAL | 75.3% | – |
| HiL-Bench | Scale AI SEAL | 39.7%† | – |
| τ³-bench Banking | τ²-bench | 44.6% | – |
| τ³-Banking (AA) | Artificial Analysis | 39.0% | 34.9% |
| ITBench SRE (AA) | Artificial Analysis | 45.8% | – |
| Analyst Agent (AA) | Artificial Analysis | 50.0% | – |
| APEX-Agents (AA) | Artificial Analysis | 37.7% | – |
| CyberBench | Vals AI | – | 69.5% |
| Finance Agent v2 | Vals AI | 51.8% | 60.6% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 3.8% | 25.4% |
| Legal Research Bench | Vals AI | 40.4% | 43.8% |
| SkillsBench | Vals AI | 62.2% | 53.0% |
| SREBench | Vals AI | 3.8% | 0.0% |
| Tax Agent Bench | Vals AI | 21.8% | 32.8% |
| Terminal-Bench 2.0 (Vals) | Vals AI | 73.2%† | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 6.1% |
| Time Horizon Index: KSP | Vals AI | 8.3% | – |
| Arena Search | Arena (LMArena) | 1226† | – |
| DeepResearch Bench | DeepResearch Bench | 54.0%† | – |
| PostTrainBench | Epoch AI Benchmarking Hub | 27.2% | – |
| ExploitBench | Epoch AI Benchmarking Hub | 47.4%† | – |
| GBAEval | Epoch AI Benchmarking Hub | 53.2%† | – |
| Vending-Bench 2 | Andon Labs | 7523.8† | – |
| AutomationBench | Artificial Analysis | 47.3% | 40.6% |
| GDP.pdf (AA) | Artificial Analysis | 21.2% | 17.4% |
| EnterpriseOps-Gym | Artificial Analysis | 46.6% | 47.3% |
| AA-Briefcase v1.1 | Artificial Analysis | 1135 | 1324 |
| Design Arena Agentic | Design Arena | 1105† | 1178† |
| RoboDojo (LLM as robot policy) | RoboDojo | 1.1† | – |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 85.3% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 72.5% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 84.4%† | – |
| ProofBench | Vals AI | 50.0% | 43.0%† |
| LiveBench Mathematics | LiveBench | 95.9% | 91.2% |
| AIME 2026 | MathArena | 100.0% | – |
| HMMT February 2026 | MathArena | 98.5% | – |
| USAMO 2026 | MathArena | 98.2% | – |
| MathArena Apex | MathArena | 80.2% | – |
| Arena Maths | Arena (LMArena) | 1500† | 1490 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 63.0% | 60.3% |
| LiveBench 1.0 Data Analysis | LiveBench | 81.6% | 76.5% |
| MMLU-Pro | Vals AI | 88.1% | 88.3% |
| LegalBench | Vals AI | 86.5% | 85.3% |
| CorpFin | Vals AI | 68.4% | 70.9% |
| TaxEval | Vals AI | 75.0% | 80.4% |
| BioMysteryBench | Vals AI | – | 64.8% |
| CaseLaw v2 | Vals AI | 66.2% | – |
| Excel Modeling Benchmark | Vals AI | 64.5% | 57.0% |
| MedCode | Vals AI | 49.1% | 49.4% |
| MedScribe | Vals AI | 86.9% | 90.1% |
| Public Benefits Bench v1.1 | Vals AI | 60.9% | 68.5% |
| DrugDiscoveryBench | Scale AI SEAL | 51.6% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 34.3% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 26.0% | 16.0% |
| Instruction following | |||
| LiveBench Language | LiveBench | 87.4% | 78.6% |
| LiveBench Instruction Following | LiveBench | 70.7% | 74.3% |
| IFBench | Artificial Analysis | 75.8% | – |
| Arena Instruction Following | Arena (LMArena) | 1475† | 1479 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1476† | 1494 |
| EQ-Bench 4 | EQ-Bench | 1295† | – |
| Arena Creative Writing | Arena (LMArena) | 1448† | 1443 |
| Arena Multi-turn | Arena (LMArena) | 1484† | 1512 |
| Arena Longer Queries | Arena (LMArena) | 1486† | 1491 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1296† | 1305 |
| MMMU-Pro | Artificial Analysis | 79.9% | – |
| MMMU-Pro (Vals) | Vals AI | 88.3% | 86.1% |
| MortgageTax | Vals AI | 68.8% | 65.4% |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 36.2%† | – |
| Code2Video-AA | Artificial Analysis | 1000 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 84.3% | 79.0% |
| Arena Document | Arena (LMArena) | 1479† | – |
| MLCR | Artificial Analysis | 28.9% | 7.2% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 160.1† | 155† |
| LiveBench 1.0 | LiveBench | 80.2% | 78.0% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 38.4 | 39.6 |
| AA Progress Index v1 | Artificial Analysis | 320 | 309.1 |
| Vals RSI Index | Vals AI | 16.5% | – |
| Vals Multimodal Index | Vals AI | 68.1% | 69.8%† |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 16.3% | – |
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
- GPT-5.5 (xhigh): 1 score revision.
- Muse Spark 1.2 (xhigh): 1 score revision.
- Muse Spark 1.2 (xhigh): 1 score revision.
- Muse Spark 1.2 (xhigh): BenchLeader Index 62.2 → 61.6.
- GPT-5.5 (xhigh): 1 new result (AA Progress Index v1).
- Muse Spark 1.2 (xhigh): 1 new result (AA Progress Index v1).
- Muse Spark 1.2 (xhigh): cost per task moved from $1.29/M to $0.81/M (37% down).
- GPT-5.5 (xhigh): cost per task moved from $2.63/M to $2.10/M (20% down).
- Muse Spark 1.2 (xhigh): cost per task moved from $0.97/M to $1.29/M (32% up).
- GPT-5.5 (xhigh): 1 new result (AA-Briefcase v1.1).
Related comparisons
- GPT-5.5 vs Claude Fable 5.2
- GPT-5.5 vs Claude Opus 5.5
- GPT-5.5 vs Gemini 4 Carbon
- Muse Spark 1.2 vs Claude Fable 5.2
- Muse Spark 1.2 vs Claude Opus 5.5
- Muse Spark 1.2 vs Gemini 4 Carbon
- Muse Spark 1.2 vs GPT-6 Astra
- GPT-5.4 vs Muse Spark 1.2
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GPT-5.5 vs Muse Spark 1.2: questions
- Is GPT-5.5 better than Muse Spark 1.2?
- GPT-5.5 (xhigh) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.2 vs 61.7, within the ±6.3 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.
- GPT-5.5 vs Muse Spark 1.2: which is cheaper, and will that change?
- Muse Spark 1.2 is cheaper today: $2.00 against $11.25 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is GPT-5.5 or Muse Spark 1.2 better for coding?
- GPT-5.5 scores higher in coding (61 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1512 for GPT-5.5 against 1534 for Muse Spark 1.2.
- Which is faster, GPT-5.5 or Muse Spark 1.2?
- Muse Spark 1.2 streams ~2× faster (192 vs 79 output tokens per second, Artificial Analysis 7-day median).
- Is GPT-5.5 or Muse Spark 1.2 better for agents and tool use?
- GPT-5.5 scores higher in agentic tasks (62 vs 56 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 39.0% for GPT-5.5 against 34.9% for Muse Spark 1.2.
More questions (4)
- Which is better for long documents?
- GPT-5.5 scores higher on long-context benchmarks (67 vs 64). Both take about 1.1M tokens: GPT-5.5 1,050,000, Muse Spark 1.2 1,048,576.
- Which has lower latency?
- Muse Spark 1.2 answers first: 7.9 s against 28.6 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 GPT-5.5 vs Muse Spark 1.2?
- Across the 51 benchmarks both have, GPT-5.5 leads 31, Muse Spark 1.2 leads 19 and 1 is a tie. 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.