Muse Spark 1.3 vs Muse Wonder
As of 13 Oct 2026, Muse Spark 1.3 (max) is the better pick for most workloads: it leads on quality (67.6 vs 66.3 on the BenchLeader Index) and costs 4.0× less.
Muse Spark 1.3 Key differences
- Muse Spark 1.3 (max) leads on quality: 67.6 vs 66.3.
- Muse Spark 1.3 (max) is stronger in agents & tools, coding, composite, human preference, long context, maths, multimodal.
- Muse Wonder (max) is stronger in knowledge, reasoning.
- Muse Spark 1.3 (max) is 4.0× cheaper ($2.00 vs $8.00 per 1M blended).
- Muse Spark 1.3 (max) streams 1.5× faster (127 vs 85 tokens per second).
Choose Muse Spark 1.3 (max) if
- long context is the priority (67 vs 66 on the category score)
- cost matters: $2.00 against $8.00 per million tokens blended
- you need fast output: 127 against 85 tokens per second
Choose Muse Wonder (max) if
- reasoning is the priority (88 vs 78 on the category score)
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 1.3 (max) | Muse Wonder (max) | Leader |
|---|---|---|---|
| Reasoning | 77.7 | 87.8 | Muse Wonder |
| Coding | 64.6 | – | not comparable |
| Agents & tools | 70.3 | – | not comparable |
| Maths | 63.6 | – | not comparable |
| Knowledge | 72.8 | 73.0 | level |
| Human preference | 69.4 | – | not comparable |
| Multimodal | 65.9 | – | not comparable |
| Long context | 66.7 | 65.5 | Muse Spark 1.3 |
| Composite | 83.6 | 78.2 | Muse Spark 1.3 |
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 1.3 (max) | Muse Wonder (max) |
|---|---|---|
| Blended price per 1M tokens | $2.00 | $8.00 |
| Input / output per 1M | $1.25 / $4.25 | $4.00 / $20.00 |
| Price per task: chat reply | $0.0018 | $0.0076 |
| Price per task: summarise a 30-page report | $0.018 | $0.060 |
| Price per task: code edit | $0.014 | $0.054 |
| Price per task: agentic coding session | $0.092 | $0.320 |
| Price per task: structured extraction | $0.0034 | $0.012 |
| Cost to run a full benchmark suite | $1.60 | $4.52 |
| Output speed | 127 tok/s | 85 tok/s |
| Time to first answer | 57.3 s | 60.8 s |
| Time to a complete answer | 61.2 s | 66.7 s |
Every benchmark
| Metric | Muse Spark 1.3 (max) | Muse Wonder (max) |
|---|---|---|
| BenchLeader Index | 67.6 | 66.3 |
| Agents & tools score | 70.3 | – |
| Coding score | 64.6 | – |
| Composite score | 83.6 | 78.2 |
| Human preference score | 69.4 | – |
| Knowledge score | 72.8 | 73.0 |
| Long context score | 66.7 | 65.5 |
| Maths score | 63.6 | – |
| Multimodal score | 65.9 | – |
| Reasoning score | 77.7 | 87.8 |
| Blended price $/M | $2.00 | $8.00 |
| Output speed | 127 tok/s | 85 tok/s |
| Time to first answer | 57.3 s | 60.8 s |
| Context window | 1.0M | 1.0M |
| FrontierMath Tiers 1–3 | 74.0% | – |
| FrontierMath Tier 4 | 46.3% | – |
| SciCode | 58.8% | – |
| ProofBench | 58.0% | – |
| LMArena Text | 1494 | – |
| LMArena Hard Prompts | 1517 | – |
| LMArena Coding | 1538 | – |
| LMArena WebDev | 1657 | – |
| LMArena Vision | 1309 | – |
| LMArena Agent | 4 | – |
| LiveBench | – | 81.2% |
| LiveBench Reasoning | – | 90.6% |
| LiveBench Coding | – | 80.7% |
| LiveBench Agentic Coding | – | 62.7% |
| LiveBench Mathematics | – | 96.5% |
| LiveBench Data Analysis | – | 81.6% |
| LiveBench Language | – | 82.9% |
| LiveBench Instruction Following | – | 73.0% |
| AA Intelligence Index v4.3.2 | 48.1 | 52.4 |
| AA-LCR | 83.0% | 80.7% |
| AA-Omniscience | 25 | 25.5 |
| GPQA Diamond (AA) | 93.5% | – |
| Humanity's Last Exam (AA) | 48.7% | 50.1% |
| SciCode (AA) | 58.8% | 60.3% |
| IOI | 56.6% | – |
| Terminal-Bench 2.1 (Vals) | 79.0% | – |
| Vals Index | 58.2 | – |
| CritPt | 24.9% | 28.3% |
| GDPval-AA v2.1 | 59.0% | 63.5% |
| τ³-Banking (AA) | 50.5% | – |
| ITBench SRE (AA) | 33.2% | – |
| Code Migration | 47.4% | – |
| CUA-bench | 5.8% | – |
| CyberBench | 72.7% | – |
| Excel Modeling Benchmark | 67.4% | – |
| Finance Agent v2 | 60.0% | – |
| Harvey's Legal Agent Benchmark | 23.8% | – |
| Legal Research Bench | 55.3% | – |
| MysteryMechanism | 36.0% | – |
| Tax Agent Bench | 72.4% | – |
| Terminal-Bench 4.0 (Vals) | 24.8% | – |
| Terminal-Bench Science | 10.0% | – |
| Vibe Code Bench 1-100 | 20.5% | – |
| Vibe Code Bench v1.1 | 85.9% | – |
| LMArena Maths | 1502 | – |
| LMArena Creative Writing | 1456 | – |
| LMArena Instruction Following | 1483 | – |
| LMArena Multi-turn | 1487 | – |
| LMArena Longer Queries | 1497 | – |
| LMArena Document | 1468 | – |
| Chess Puzzles | 38.0% | – |
| Mystery Game Puzzles | 25.0% | – |
| CursorBench | 41.6% | – |
| Terminal-Bench 4.0 (AA) | 33.3% | 52.0% |
| Terminal-Bench 2.1 (AA) | 84.3% | – |
| AutomationBench | 57.9% | 68.1% |
| GDP.pdf | 26.6% | 30.6% |
| MLCR | 43.3% | – |
| Harvey LAB-AA v1.1 | 8.9% | – |
| AA-Omniscience: accuracy | 43.6% | 41.1% |
| AA-Omniscience: non-hallucination | 67.1% | 73.5% |
| AA-Briefcase v1.1 | 1581 | 1659 |
| FrontierCode 1.1 (AA) | 40.6% | – |
| Terminal-Bench-Science 0.1 (AA) | 10.9% | – |
| AA-3D | 1035 | – |
Data as of 2026-10-13. Best configuration of each model; every score links to its source on the model pages.
Muse Spark 1.3 vs Muse Wonder: questions
- Is Muse Spark 1.3 better than Muse Wonder?
- Muse Spark 1.3 (max) leads on quality: 67.6 vs 66.3. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 (max) is ahead overall as of 2026-10-13, but check the category scores for your use.
- Which is cheaper, Muse Spark 1.3 or Muse Wonder?
- Muse Spark 1.3 is cheaper: $2.00 against $8.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Muse Spark 1.3 or Muse Wonder?
- Muse Spark 1.3 streams faster: 127 against 85 output tokens per second.
- Which has the larger context window?
- Both accept 1.0M tokens of context.