GPT-6 Luna vs Muse Spark 1.3
GPT-6 Luna 
Muse Spark 1.3 Verdict
- Muse Spark 1.3 (max) leads on quality: 68.9 vs 61.2.
- GPT-6 Luna (max) is stronger in long context.
- Muse Spark 1.3 (max) is stronger in composite, knowledge, multimodal, reasoning, agents & tools, coding, human preference, maths.
- GPT-6 Luna (max) is 10× cheaper ($0.200 vs $2.00 per 1M blended).
- Muse Spark 1.3 (max) streams 1.4× faster (221 vs 157 tokens per second).
| Metric | GPT-6 Luna (max) | Muse Spark 1.3 (max) |
|---|---|---|
| BenchLeader Index | 61.2 | 68.9 |
| Composite score | 73.9 | 86.9 |
| Knowledge score | 63.2 | 74.4 |
| Long context score | 67.5 | 67.3 |
| Multimodal score | 59.2 | 67.4 |
| Reasoning score | 76.1 | 80.3 |
| Agents & tools score | – | 71.0 |
| Coding score | – | 67.0 |
| Human preference score | – | 69.8 |
| Maths score | – | 65.9 |
| Blended price $/M | $0.200 | $2.00 |
| Output speed | 157 tok/s | 221 tok/s |
| Time to first answer | 142.6 s | 30.3 s |
| Context window | 1.1M | 1.0M |
| FrontierMath Tiers 1–3 | – | 74.0% |
| FrontierMath Tier 4 | – | 46.3% |
| SciCode | – | 58.8% |
| LMArena Text | – | 1493 |
| LMArena Hard Prompts | – | 1516 |
| LMArena Coding | – | 1537 |
| LMArena WebDev | – | 1652 |
| LMArena Vision | – | 1315 |
| LMArena Agent | – | 4.2 |
| AA Intelligence Index | 37.3 | 48.1 |
| AA-LCR | 83.3% | 83.0% |
| MMMU-Pro | 75.5% | – |
| AA-Omniscience | 0.7 | 25 |
| GPQA Diamond (AA) | – | 93.5% |
| Humanity's Last Exam (AA) | 38.5% | 48.7% |
| SciCode (AA) | 54.6% | 58.8% |
| IOI | – | 56.6% |
| Terminal-Bench 2.1 (Vals) | – | 79.0% |
| Vals Index | – | 64.5 |
| CritPt | 19.4% | 24.9% |
| GDPval (AA) | 43.4% | 58.7% |
| τ²-Bench Banking (AA) | – | 50.5% |
| Code Migration | – | 47.4% |
| 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% |
| Terminal-Bench 4.0 (Vals) | – | 27.8% |
| Terminal-Bench Science | – | 14.3% |
| Vibe Code Bench 1-100 | – | 20.5% |
| Vibe Code Bench v1.1 | – | 85.9% |
| LMArena Maths | – | 1496 |
| LMArena Creative Writing | – | 1453 |
| LMArena Instruction Following | – | 1483 |
| LMArena Multi-turn | – | 1493 |
| LMArena Longer Queries | – | 1506 |
| LMArena Document | – | 1468 |
| Chess Puzzles | – | 38.0% |
| Mystery Game Puzzles | – | 25.0% |
| CursorBench | – | 41.6% |
| Terminal-Bench 4.0 (AA) | 12.6% | 33.3% |
| Terminal-Bench 2.1 (AA) | – | 84.3% |
| AutomationBench | 53.2% | 57.9% |
| GDP.pdf | 20.4% | 26.6% |
| MLCR | 16.1% | 43.3% |
| AA-Omniscience: accuracy | 43.8% | 43.6% |
| AA-Omniscience: non-hallucination | 23.3% | 67.1% |
| AA-Briefcase | 1299 | 1597 |
Data as of 2026-09-23. Best configuration of each model; every score links to its source on the model pages.
GPT-6 Luna vs Muse Spark 1.3: questions
- Is GPT-6 Luna better than Muse Spark 1.3?
- Muse Spark 1.3 (max) leads on quality: 68.9 vs 61.2. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 (max) is ahead overall as of 2026-09-23, but check the category scores for your use.
- Which is cheaper, GPT-6 Luna or Muse Spark 1.3?
- GPT-6 Luna is cheaper: $0.200 against $2.00 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-6 Luna or Muse Spark 1.3?
- Muse Spark 1.3 streams faster: 221 against 157 output tokens per second.
- Which has the larger context window?
- GPT-6 Luna accepts more context: 1.1M against 1.0M tokens.