GPT-6 Astra vs Muse Spark 1.1
GPT-6 Astra 
Muse Spark 1.1 Verdict
- GPT-6 Astra (max) leads on quality: 70.6 vs 64.9.
- GPT-6 Astra (max) is stronger in agents & tools, coding, composite, knowledge, maths, reasoning.
- Muse Spark 1.1 is stronger in human preference, instruction following, long context, multimodal.
- Muse Spark 1.1 is 11× cheaper ($2.00 vs $22.00 per 1M blended).
- Muse Spark 1.1 streams 3.6× faster (194 vs 54 tokens per second).
| Metric | GPT-6 Astra (max) | Muse Spark 1.1 |
|---|---|---|
| BenchLeader Index | 70.6 | 64.9 |
| Agents & tools score | 68.2 | 62.7 |
| Coding score | 79.0 | 68.2 |
| Composite score | 73.1 | 72.2 |
| Knowledge score | 79.8 | 73.1 |
| Maths score | 77.0 | 52.2 |
| Reasoning score | 70.9 | 68.8 |
| Human preference score | – | 66.0 |
| Instruction following score | – | 77.8 |
| Long context score | – | 65.3 |
| Multimodal score | – | 64.9 |
| Blended price $/M | $22.00 | $2.00 |
| Output speed | 54 tok/s | 194 tok/s |
| Time to first answer | 328.6 s | 2.0 s |
| Context window | 1.1M | 1.0M |
| GPQA Diamond | 95.8% | – |
| FrontierMath Tiers 1–3 | 93.7% | – |
| FrontierMath Tier 4 | 97.6% | – |
| OTIS Mock AIME | 100.0% | – |
| SimpleQA Verified | 75.6% | 57.8% |
| Terminal-Bench | 58.2% | – |
| SciCode | 56.5% | 58.2% |
| APEX-Agents | – | 41.9% |
| FrontierCode | 53.3% | – |
| ProofBench | – | 39.0% |
| Epoch Capabilities Index | – | 154.6 |
| LMArena Text | – | 1492 |
| LMArena Hard Prompts | – | 1511 |
| LMArena Coding | – | 1531 |
| LMArena WebDev | 1796 | 1541 |
| LMArena Vision | – | 1293 |
| LMArena Agent | 12.5 | -2.6 |
| 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 | – | 34.3 |
| AA-LCR | – | 77.7% |
| AA-Omniscience | – | 28.1 |
| GPQA Diamond (AA) | – | 89.8% |
| Humanity's Last Exam (AA) | – | 46.2% |
| SciCode (AA) | – | 58.8% |
| Terminal-Bench 2.1 (Vals) | 87.3% | – |
| Vals Index | 66.6 | – |
| SWE-Bench Pro | – | 61.5% |
| MCP Atlas | – | 88.1% |
| MultiChallenge | – | 75.3% |
| PRBench Finance | – | 55.0% |
| PRBench Legal | – | 57.0% |
| MultiNRC | – | 65.6% |
| EQ-Bench 4 | – | 1260 |
| 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.