GPT-5.6 Terra vs Muse Spark 1.3
GPT-5.6 Terra 
Muse Spark 1.3 Verdict
- GPT-5.6 Terra (xhigh) and Muse Spark 1.3 (xhigh) are level on quality (64.2 vs 63.9).
- GPT-5.6 Terra (xhigh) is stronger in agents & tools, human preference, instruction following, maths, reasoning.
- Muse Spark 1.3 (xhigh) is stronger in coding, composite, knowledge, long context, multimodal.
- Muse Spark 1.3 (xhigh) is 2.3× cheaper ($2.00 vs $4.50 per 1M blended).
- Muse Spark 1.3 (xhigh) streams 2.1× faster (193 vs 93 tokens per second).
| Metric | GPT-5.6 Terra (xhigh) | Muse Spark 1.3 (xhigh) |
|---|---|---|
| BenchLeader Index | 64.2 | 63.9 |
| Agents & tools score | 69.6 | 60.4 |
| Coding score | 63.7 | 70.8 |
| Composite score | 77.1 | 78.6 |
| Human preference score | 66.3 | – |
| Instruction following score | 65.0 | – |
| Knowledge score | 60.9 | 75.0 |
| Long context score | 66.0 | 68.1 |
| Maths score | 71.0 | – |
| Multimodal score | 63.0 | 66.6 |
| Reasoning score | 58.2 | – |
| Blended price $/M | $4.50 | $2.00 |
| Output speed | 93 tok/s | 193 tok/s |
| Time to first answer | 32.5 s | 40.0 s |
| Context window | 1M | 1M |
| SimpleBench | 48.9% | – |
| SciCode | 51.6% | – |
| ProofBench | 74.0% | – |
| LMArena Text | 1466 | – |
| LMArena Hard Prompts | 1491 | – |
| LMArena Coding | 1519 | – |
| LMArena WebDev | 1521 | 1625 |
| LMArena Vision | 1269 | – |
| LMArena Agent | 1.5 | – |
| LiveBench | – | 81.6% |
| LiveBench Reasoning | – | 89.7% |
| LiveBench Coding | – | 81.1% |
| LiveBench Agentic Coding | – | 64.1% |
| LiveBench Mathematics | – | 96.0% |
| LiveBench Data Analysis | – | 79.6% |
| LiveBench Language | – | 82.8% |
| AA Intelligence Index | 38.2 | 45.2 |
| IFBench | 66.3% | – |
| AA-LCR | 79.0% | 83.0% |
| MMMU-Pro | 79.5% | 82.0% |
| AA-Omniscience | -3.0 | 23.1 |
| Terminal-Bench Hard | 62.9% | – |
| GPQA Diamond (AA) | 90.8% | 94.1% |
| Humanity's Last Exam (AA) | 41.9% | 47.5% |
| SciCode (AA) | 52.3% | 59.7% |
| τ²-Bench Telecom (AA) | 80.4% | – |
| LiveCodeBench | 85.9% | – |
| MMLU-Pro | 86.7% | – |
| IOI | 65.3% | – |
| CorpFin | 65.3% | – |
| TaxEval | 76.2% | – |
| Terminal-Bench 2.1 (Vals) | – | 72.3% |
| GPQA Diamond (Vals) | 90.9% | – |
| Vals Index | – | 60.3 |
| ARC-AGI-1 | 94.0% | – |
| ARC-AGI-2 | 74.2% | – |
| ARC-AGI-3 | 0.7% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.