Claude Fable 5.1 vs Muse Spark Open
As of 18 Oct 2026, Claude Fable 5.1 (max) leads on quality (69.9 vs 61.2 on the BenchLeader Index), but Muse Spark Open (xhigh) costs 10× less, so it is the better buy unless you need the extra quality.
Claude Fable 5.1 
Muse Spark Open Key differences
- Claude Fable 5.1 (max) leads on quality: 69.9 vs 61.2.
- Claude Fable 5.1 (max) is stronger in agents & tools, coding, composite, human preference, knowledge, long context, maths, multimodal, reasoning.
- Muse Spark Open (xhigh) is 10× cheaper ($2.00 vs $20.00 per 1M blended).
- Muse Spark Open (xhigh) streams 2.0× faster (140 vs 71 tokens per second).
Choose Claude Fable 5.1 (max) if
- reasoning is the priority (77 vs 66 on the category score)
- knowledge is the priority (77 vs 73 on the category score)
- long context is the priority (68 vs 64 on the category score)
Choose Muse Spark Open (xhigh) if
- cost matters: $2.00 against $20.00 per million tokens blended
- you need fast output: 140 against 71 tokens per second
- the wait for the first word matters: 15.0 s against 173.6 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 | Claude Fable 5.1 (max) | Muse Spark Open (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 76.8 | 65.5 | Claude Fable 5.1 |
| Coding | 75.1 | – | not comparable |
| Agents & tools | 60.6 | – | not comparable |
| Maths | 72.9 | – | not comparable |
| Knowledge | 77.4 | 72.5 | Claude Fable 5.1 |
| Human preference | 70.2 | – | not comparable |
| Multimodal | 67.0 | 64.1 | Claude Fable 5.1 |
| Long context | 67.8 | 64.2 | Claude Fable 5.1 |
| Composite | 82.0 | 73.1 | Claude Fable 5.1 |
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 | Claude Fable 5.1 (max) | Muse Spark Open (xhigh) |
|---|---|---|
| Blended price per 1M tokens | $20.00 | $2.00 |
| Input / output per 1M | $10.00 / $50.00 | $1.25 / $4.25 |
| Price per task: chat reply | $0.019 | $0.0018 |
| Price per task: summarise a 30-page report | $0.150 | $0.018 |
| Price per task: code edit | $0.135 | $0.014 |
| Price per task: agentic coding session | $0.800 | $0.092 |
| Price per task: structured extraction | $0.030 | $0.0034 |
| Cost to run a full benchmark suite | $7.63 | $0.844 |
| Output speed | 71 tok/s | 140 tok/s |
| Time to first answer | 173.6 s | 15.0 s |
| Time to a complete answer | 180.7 s | 18.6 s |
Every benchmark
| Metric | Claude Fable 5.1 (max) | Muse Spark Open (xhigh) |
|---|---|---|
| BenchLeader Index | 69.9 | 61.2 |
| Agents & tools score | 60.6 | – |
| Coding score | 75.1 | – |
| Composite score | 82.0 | 73.1 |
| Human preference score | 70.2 | – |
| Knowledge score | 77.4 | 72.5 |
| Long context score | 67.8 | 64.2 |
| Maths score | 72.9 | – |
| Multimodal score | 67.0 | 64.1 |
| Reasoning score | 76.8 | 65.5 |
| Blended price $/M | $20.00 | $2.00 |
| Output speed | 71 tok/s | 140 tok/s |
| Time to first answer | 173.6 s | 15.0 s |
| Context window | 1M | 1.0M |
| FrontierMath Tiers 1–3 | 90.2% | – |
| FrontierMath Tier 4 | 87.8% | – |
| OTIS Mock AIME | 100.0% | – |
| SimpleQA Verified | 70.8% | – |
| Terminal-Bench | 57.9% | – |
| SciCode | 63.1% | – |
| WeirdML | 92.9% | – |
| ProofBench | 100.0% | – |
| Arena Text | 1502 | – |
| Arena Hard Prompts | 1521 | – |
| Arena Coding | 1537 | – |
| Arena WebDev | 1741 | – |
| Arena Vision | 1318 | – |
| Arena Agent | 14 | – |
| LiveBench | 83.4% | – |
| LiveBench Reasoning | 91.7% | – |
| LiveBench Coding | 86.4% | – |
| LiveBench Agentic Coding | 66.1% | – |
| LiveBench Mathematics | 97.0% | – |
| LiveBench Data Analysis | 80.3% | – |
| LiveBench Language | 89.5% | – |
| LiveBench Instruction Following | 73.0% | – |
| AA Intelligence Index v4.3.2 | 53.4 | 38.9 |
| AA-LCR | 85.3% | 78.3% |
| MMMU-Pro | – | 80.9% |
| AA-Omniscience | 43.5 | 24.6 |
| GPQA Diamond (AA) | 93.7% | 89.0% |
| Humanity's Last Exam (AA) | 59.1% | 43.9% |
| SciCode (AA) | 63.1% | 58.5% |
| Vals Index | – | 46.6 |
| ARC-AGI-1 | 97.5% | – |
| ARC-AGI-2 | 90.0% | – |
| CritPt | 29.7% | 14.9% |
| GDPval-AA v2.1 | 62.7% | 45.1% |
| τ³-Banking (AA) | 47.2% | – |
| ITBench SRE (AA) | 49.5% | – |
| Analyst Agent (AA) | 57.5% | – |
| Code Migration | – | 21.2% |
| CUA-bench | 13.2% | – |
| Excel Modeling Benchmark | – | 53.7% |
| Finance Agent v2 | – | 61.3% |
| Harvey's Legal Agent Benchmark | – | 16.7% |
| Legal Research Bench | – | 38.5% |
| Tax Agent Bench | – | 26.3% |
| Terminal-Bench 4.0 (Vals) | – | 6.6% |
| Vibe Code Bench v1.1 | – | 76.2% |
| Arena Maths | 1525 | – |
| Arena Creative Writing | 1485 | – |
| Arena Instruction Following | 1499 | – |
| Arena Multi-turn | 1487 | – |
| Arena Longer Queries | 1509 | – |
| Arena Document | 1493 | – |
| Chess Puzzles | 48.0% | – |
| EBR-bench | 57.1% | – |
| Mystery Game Puzzles | 58.0% | – |
| CursorBench | 51.8% | – |
| GDP.pdf | 27.6% | – |
| FrontierSWE | 56.3% | – |
| Terminal-Bench 4.0 (AA) | 52.0% | 8.1% |
| Terminal-Bench 2.1 (AA) | 91.4% | 76.4% |
| AutomationBench | 59.4% | 49.7% |
| GDP.pdf | 26.2% | 18.6% |
| MLCR | 71.1% | – |
| Harvey LAB-AA v1.1 | 6.4% | – |
| AA-Omniscience: accuracy | 67.2% | 39.3% |
| AA-Omniscience: non-hallucination | 27.4% | 75.9% |
| AA-Briefcase v1.1 | 1672 | 1279 |
| FrontierCode 1.1 (AA) | 49.0% | – |
| Terminal-Bench-Science 0.1 (AA) | 43.3% | – |
| AA Cyber Index | 2501.9% | – |
| CWE-Bench (AA) | 50.8% | – |
| DeepSec-Bench (AA) | 23.5% | – |
| CyberGym end-to-end (AA) | 0.8% | – |
| AA-3D | 1133 | – |
| 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.
Claude Fable 5.1 vs Muse Spark Open: questions
- Is Claude Fable 5.1 better than Muse Spark Open?
- Claude Fable 5.1 (max) leads on quality: 69.9 vs 61.2. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.1 (max) is ahead overall as of 2026-10-18, but check the category scores for your use.
- Which is cheaper, Claude Fable 5.1 or Muse Spark Open?
- Muse Spark Open is cheaper: $2.00 against $20.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Fable 5.1 or Muse Spark Open?
- Muse Spark Open streams faster: 140 against 71 output tokens per second.
- Which has the larger context window?
- Muse Spark Open accepts more context: 1.0M against 1M tokens.