GPT-6 Astra vs Muse Spark
GPT-6 Astra 
Muse Spark Verdict
- GPT-6 Astra (max) leads on quality: 70.6 vs 65.4.
- GPT-6 Astra (max) is stronger in agents & tools, coding, composite, knowledge, maths, reasoning.
- Muse Spark is stronger in human preference, instruction following, long context, multimodal.
| Metric | GPT-6 Astra (max) | Muse Spark |
|---|---|---|
| BenchLeader Index | 70.6 | 65.4 |
| Agents & tools score | 68.2 | 66.3 |
| Coding score | 79.0 | 66.0 |
| Composite score | 73.1 | 68.4 |
| Knowledge score | 79.8 | 64.5 |
| Maths score | 77.0 | 56.3 |
| Reasoning score | 70.9 | 70.0 |
| Human preference score | – | 69.0 |
| Instruction following score | – | 79.6 |
| Long context score | – | 65.5 |
| Multimodal score | – | 65.9 |
| Blended price $/M | $22.00 | – |
| Output speed | 54 tok/s | – |
| Time to first answer | 328.6 s | – |
| Context window | 1.1M | 262k |
| GPQA Diamond | 95.8% | 89.8% |
| FrontierMath Tiers 1–3 | 93.7% | – |
| FrontierMath Tier 4 | 97.6% | – |
| OTIS Mock AIME | 100.0% | 88.9% |
| SimpleQA Verified | 75.6% | – |
| Humanity's Last Exam | – | 40.6% |
| Terminal-Bench | 58.2% | – |
| SciCode | 56.5% | 51.5% |
| FrontierCode | 53.3% | – |
| ProofBench | – | 17.0% |
| Epoch Capabilities Index | – | 152.1 |
| LMArena Text | – | 1488 |
| LMArena Hard Prompts | – | 1505 |
| LMArena Coding | – | 1526 |
| LMArena WebDev | 1796 | – |
| LMArena Vision | – | 1306 |
| LMArena Agent | 12.5 | – |
| LiveBench | 82.2% | – |
| LiveBench Reasoning | 92.7% | – |
| LiveBench Coding | 80.4% | – |
| LiveBench Agentic Coding | 57.3% | – |
| LiveBench Mathematics | 96.8% | – |
| LiveBench Data Analysis | 83.0% | – |
| LiveBench Language | 89.4% | – |
| AA Intelligence Index | – | 31.3 |
| IFBench | – | 75.9% |
| AA-LCR | – | 78.0% |
| MMMU-Pro | – | 80.5% |
| AA-Omniscience | – | 7.2 |
| Terminal-Bench Hard | – | 45.5% |
| GPQA Diamond (AA) | – | 88.4% |
| Humanity's Last Exam (AA) | – | 40.7% |
| τ²-Bench Telecom (AA) | – | 91.5% |
| AIME (Vals) | – | 96.9% |
| MMLU-Pro | – | 87.3% |
| LegalBench | – | 84.2% |
| CorpFin | – | 65.1% |
| TaxEval | – | 77.7% |
| Terminal-Bench 2.1 (Vals) | 87.3% | – |
| SWE-bench (Vals) | – | 74.4% |
| GPQA Diamond (Vals) | – | 89.7% |
| Vals Index | 66.6 | – |
| SWE-Bench Pro | – | 55.0% |
| MCP Atlas | – | 82.2% |
| MultiChallenge | – | 75.5% |
| PRBench Finance | – | 52.4% |
| PRBench Legal | – | 52.3% |
| MultiNRC | – | 59.0% |
| TutorBench | – | 68.5% |
| ARC-AGI-1 | 97.5% | – |
| ARC-AGI-2 | 95.0% | – |
| ARC-AGI-3 | 62.7% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.