GPT-6.1 Sol vs Muse Spark Open
As of 18 Oct 2026, GPT-6.1 Sol (max) leads on quality (69.1 vs 61.2 on the BenchLeader Index), but Muse Spark Open (xhigh) costs 2.0× less, so it is the better buy unless you need the extra quality.
GPT-6.1 Sol 
Muse Spark Open Key differences
- GPT-6.1 Sol (max) leads on quality: 69.1 vs 61.2.
- GPT-6.1 Sol (max) is stronger in agents & tools, coding, composite, human preference, knowledge, long context, maths, multimodal, reasoning.
- Muse Spark Open (xhigh) is 2.0× cheaper ($2.00 vs $4.00 per 1M blended).
- Muse Spark Open (xhigh) streams 2.2× faster (140 vs 64 tokens per second).
Choose GPT-6.1 Sol (max) if
- reasoning is the priority (76 vs 66 on the category score)
- knowledge is the priority (78 vs 73 on the category score)
- long context is the priority (67 vs 64 on the category score)
Choose Muse Spark Open (xhigh) if
- cost matters: $2.00 against $4.00 per million tokens blended
- you need fast output: 140 against 64 tokens per second
- the wait for the first word matters: 15.0 s against 241.6 s to first answer
- you want to run it yourself: its weights are open
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-6.1 Sol (max) | Muse Spark Open (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 75.9 | 65.5 | GPT-6.1 Sol |
| Coding | 72.5 | – | not comparable |
| Agents & tools | 64.4 | – | not comparable |
| Maths | 72.4 | – | not comparable |
| Knowledge | 78.3 | 72.5 | GPT-6.1 Sol |
| Human preference | 67.9 | – | not comparable |
| Multimodal | 66.2 | 64.1 | GPT-6.1 Sol |
| Long context | 66.6 | 64.2 | GPT-6.1 Sol |
| Composite | 78.5 | 73.1 | GPT-6.1 Sol |
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 | GPT-6.1 Sol (max) | Muse Spark Open (xhigh) |
|---|---|---|
| Blended price per 1M tokens | $4.00 | $2.00 |
| Input / output per 1M | $2.00 / $10.00 | $1.25 / $4.25 |
| Price per task: chat reply | $0.0038 | $0.0018 |
| Price per task: summarise 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 | $0.724 | $0.844 |
| Output speed | 64 tok/s | 140 tok/s |
| Time to first answer | 241.6 s | 15.0 s |
| Time to a complete answer | 249.4 s | 18.6 s |
Every benchmark
| Metric | GPT-6.1 Sol (max) | Muse Spark Open (xhigh) |
|---|---|---|
| BenchLeader Index | 69.1 | 61.2 |
| Agents & tools score | 64.4 | – |
| Coding score | 72.5 | – |
| Composite score | 78.5 | 73.1 |
| Human preference score | 67.9 | – |
| Knowledge score | 78.3 | 72.5 |
| Long context score | 66.6 | 64.2 |
| Maths score | 72.4 | – |
| Multimodal score | 66.2 | 64.1 |
| Reasoning score | 75.9 | 65.5 |
| Blended price $/M | $4.00 | $2.00 |
| Output speed | 64 tok/s | 140 tok/s |
| Time to first answer | 241.6 s | 15.0 s |
| Context window | 1.1M | 1.0M |
| GPQA Diamond | 95.4% | – |
| FrontierMath Tiers 1–3 | 93.7% | – |
| FrontierMath Tier 4 | 100.0% | – |
| OTIS Mock AIME | 100.0% | – |
| SimpleQA Verified | 73.9% | – |
| Terminal-Bench | 58.2% | – |
| SciCode | 54.2% | – |
| APEX-Agents | 60.0% | – |
| Arena Text | 1484 | – |
| Arena Hard Prompts | 1506 | – |
| Arena Coding | 1540 | – |
| Arena WebDev | 1756 | – |
| Arena Vision | 1288 | – |
| Arena Agent | 13.6 | – |
| LiveBench | 81.6% | – |
| LiveBench Reasoning | 92.6% | – |
| LiveBench Coding | 80.4% | – |
| LiveBench Agentic Coding | 54.5% | – |
| LiveBench Mathematics | 96.8% | – |
| LiveBench Data Analysis | 82.7% | – |
| LiveBench Language | 90.1% | – |
| LiveBench Instruction Following | 74.2% | – |
| AA Intelligence Index v4.3.2 | 51.8 | 38.9 |
| AA-LCR | 83.0% | 78.3% |
| MMMU-Pro | 86.0% | 80.9% |
| AA-Omniscience | 41.5 | 24.6 |
| GPQA Diamond (AA) | – | 89.0% |
| Humanity's Last Exam (AA) | 52.9% | 43.9% |
| SciCode (AA) | 54.2% | 58.5% |
| IOI | 96.9% | – |
| Vals Index | 61.1 | 46.6 |
| ARC-AGI-1 | 96.5% | – |
| ARC-AGI-2 | 94.2% | – |
| ARC-AGI-3 | 96.2% | – |
| CritPt | 31.7% | 14.9% |
| GDPval-AA v2.1 | 54.7% | 45.1% |
| Analyst Agent (AA) | 50.0% | – |
| BioMysteryBench | 79.6% | – |
| Code Migration | 65.1% | 21.2% |
| CyberBench | 39.3% | – |
| Excel Modeling Benchmark | 70.8% | 53.7% |
| Finance Agent v2 | 52.0% | 61.3% |
| Harvey's Legal Agent Benchmark | 5.4% | 16.7% |
| Legal Research Bench | 38.5% | 38.5% |
| MedCode | 48.8% | – |
| MedScribe | 86.5% | – |
| MysteryMechanism | 46.4% | – |
| ProgramBench | 3.0% | – |
| Public Benefits Bench | 59.3% | – |
| SAGE | 46.5% | – |
| SREBench | 50.8% | – |
| Tax Agent Bench | 21.8% | 26.3% |
| Terminal-Bench 4.0 (Vals) | 55.0% | 6.6% |
| Terminal-Bench Science | 52.9% | – |
| Vibe Code Bench v1.1 | 88.9% | 76.2% |
| Arena Maths | 1494 | – |
| Arena Creative Writing | 1458 | – |
| Arena Instruction Following | 1487 | – |
| Arena Multi-turn | 1486 | – |
| Arena Longer Queries | 1492 | – |
| Arena Search | 1250 | – |
| Chess Puzzles | 68.0% | – |
| EBR-bench | 54.3% | – |
| Mystery Game Puzzles | 80.0% | – |
| ALE-Bench | 2743.8 | – |
| GDP.pdf | 35.0% | – |
| Terminal-Bench 4.0 (AA) | 56.1% | 8.1% |
| Terminal-Bench 2.1 (AA) | – | 76.4% |
| AutomationBench | 64.9% | 49.7% |
| GDP.pdf | 31.0% | 18.6% |
| MLCR | 33.9% | – |
| Harvey LAB-AA v1.1 | 6.9% | – |
| AA-Omniscience: accuracy | 62.1% | 39.3% |
| AA-Omniscience: non-hallucination | 45.7% | 75.9% |
| AA-Briefcase v1.1 | 1557 | 1279 |
| FrontierCode 1.1 (AA) | 49.1% | – |
| Terminal-Bench-Science 0.1 (AA) | 58.1% | – |
| AA-3D | 1118 | – |
| AA Openness Index | – | 27.8 |
Data as of 2026-10-18. Best configuration of each model; every score links to its source on the model pages.
GPT-6.1 Sol vs Muse Spark Open: questions
- Is GPT-6.1 Sol better than Muse Spark Open?
- GPT-6.1 Sol (max) leads on quality: 69.1 vs 61.2. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Sol (max) is ahead overall as of 2026-10-18, but check the category scores for your use.
- Which is cheaper, GPT-6.1 Sol or Muse Spark Open?
- Muse Spark Open is cheaper: $2.00 against $4.00 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-6.1 Sol or Muse Spark Open?
- Muse Spark Open streams faster: 140 against 64 output tokens per second.
- Which has the larger context window?
- GPT-6.1 Sol accepts more context: 1.1M against 1.0M tokens.