Claude Opus 4.8 vs Muse Spark 1.1
Claude Opus 4.8 
Muse Spark 1.1 Verdict
- Claude Opus 4.8 and Muse Spark 1.1 are level on quality (64.7 vs 64.9).
- Claude Opus 4.8 is stronger in agents & tools, composite.
- Muse Spark 1.1 is stronger in coding, human preference, instruction following, knowledge, multimodal, reasoning, maths.
- Muse Spark 1.1 is 5.0× cheaper ($2.00 vs $10.00 per 1M blended).
- Muse Spark 1.1 streams 3.4× faster (194 vs 58 tokens per second).
| Metric | Claude Opus 4.8 | Muse Spark 1.1 |
|---|---|---|
| BenchLeader Index | 64.7 | 64.9 |
| Agents & tools score | 65.0 | 62.7 |
| Coding score | 65.7 | 68.2 |
| Composite score | 81.9 | 72.2 |
| Human preference score | 65.6 | 66.0 |
| Instruction following score | 61.6 | 77.8 |
| Knowledge score | 66.3 | 73.1 |
| Long context score | 65.3 | 65.3 |
| Multimodal score | 64.4 | 64.9 |
| Reasoning score | 64.2 | 68.8 |
| Maths score | – | 52.2 |
| Blended price $/M | $10.00 | $2.00 |
| Output speed | 58 tok/s | 194 tok/s |
| Time to first answer | 29.5 s | 2.0 s |
| Context window | 1M | 1.0M |
| SimpleQA Verified | – | 57.8% |
| SimpleBench | 64.8% | – |
| SciCode | – | 58.2% |
| Remote Labor Index | 8.3% | – |
| APEX-Agents | – | 41.9% |
| FrontierCode | 46.5% | – |
| ProofBench | – | 39.0% |
| GSO-Bench | 47.1% | – |
| Epoch Capabilities Index | 158.3 | 154.6 |
| LMArena Text | 1473 | 1492 |
| LMArena Hard Prompts | 1503 | 1511 |
| LMArena Coding | 1527 | 1531 |
| LMArena WebDev | 1540 | 1541 |
| LMArena Vision | 1289 | 1293 |
| LMArena Agent | – | -2.6 |
| AA Intelligence Index | 42.0 | 34.3 |
| IFBench | 62.2% | – |
| AA-LCR | 77.7% | 77.7% |
| AA-Omniscience | 28.8 | 28.1 |
| Terminal-Bench Hard | 58.3% | – |
| GPQA Diamond (AA) | 92.0% | 89.8% |
| Humanity's Last Exam (AA) | 48.7% | 46.2% |
| SciCode (AA) | 54.4% | 58.8% |
| τ²-Bench Telecom (AA) | 94.4% | – |
| LiveCodeBench | 87.8% | – |
| MMLU-Pro | 89.6% | – |
| LegalBench | 83.6% | – |
| CorpFin | 66.7% | – |
| TaxEval | 75.6% | – |
| Terminal-Bench 2.1 (Vals) | 71.9% | – |
| SWE-bench (Vals) | 88.6% | – |
| GPQA Diamond (Vals) | 92.4% | – |
| Vals Index | 60.9 | – |
| SWE-Bench Pro | – | 61.5% |
| MCP Atlas | – | 88.1% |
| MultiChallenge | – | 75.3% |
| PRBench Finance | – | 55.0% |
| PRBench Legal | – | 57.0% |
| MultiNRC | – | 65.6% |
| HiL-Bench | 35.3% | – |
| EQ-Bench 4 | 1281 | 1260 |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.