GPT-5.4 Pro vs Muse Spark 1.2
GPT-5.4 Pro 
Muse Spark 1.2 Verdict
- GPT-5.4 Pro leads on quality: 64.2 vs 62.6.
- GPT-5.4 Pro is stronger in instruction following, multimodal, reasoning.
- Muse Spark 1.2 is stronger in knowledge, coding, composite, long context, maths.
- Muse Spark 1.2 is 34× cheaper ($2.00 vs $67.50 per 1M blended).
- Muse Spark 1.2 streams 219.4× faster (219 vs 1 tokens per second).
| Metric | GPT-5.4 Pro | Muse Spark 1.2 |
|---|---|---|
| BenchLeader Index | 64.2 | 62.6 |
| Instruction following score | 67.3 | – |
| Knowledge score | 73.2 | 76.9 |
| Multimodal score | 69.8 | – |
| Reasoning score | 75.1 | 70.2 |
| Coding score | – | 66.5 |
| Composite score | – | 79.1 |
| Long context score | – | 66.0 |
| Maths score | – | 54.3 |
| Blended price $/M | $67.50 | $2.00 |
| Output speed | 1 tok/s | 219 tok/s |
| Time to first answer | 6.7 s | 23.7 s |
| Context window | 1.1M | 1.0M |
| Humanity's Last Exam | 44.3% | – |
| SimpleBench | 74.1% | 74.5% |
| ProofBench | – | 43.0% |
| Epoch Capabilities Index | 158.9 | 155.5 |
| AA Intelligence Index | – | 39.8 |
| AA-LCR | – | 79.0% |
| AA-Omniscience | – | 27.2 |
| GPQA Diamond (AA) | – | 90.4% |
| Humanity's Last Exam (AA) | – | 45.5% |
| SciCode (AA) | – | 57.4% |
| IOI | – | 49.5% |
| MultiChallenge | 69.2% | – |
| VISTA | 53.9% | – |
| MultiNRC | 62.3% | – |
| TutorBench | 56.6% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.