Muse Spark 1.3 (xHigh): benchmark results
Provider: Meta. Released 2026-09-02. Access: API.
Aggregate Rating 1859 ± 12, rank #59 of 2168 rated models, from 129 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GPQA Diamond | 94.14 | Accuracy (%) | 98.9 |
| Chatbot Arena (Vision - Chinese) | 1361 | Arena Score | 97.6 |
| LiveBench TypeScript | 60 | Score | 96.4 |
| LiveBench Paraphrase | 78.62 | Score | 95.7 |
| LiveBench Simplify | 72.52 | Score | 95.7 |
| Tau3 Banking | 47.22 | Success Rate (%) | 95.7 |
| AA Long Context Reasoning | 83 | Accuracy (%) | 95.1 |
| Epoch AI - Scicode | 59.72 | Score | 95 |
| AA SciCode | 59.72 | Accuracy (%) | 94.9 |
| Artificial Analysis Intelligence Index | 45.07 | Intelligence Index | 94.8 |
| OTIS Mock AIME 2024-25 | 99.17 | Accuracy (%) | 94.6 |
| AA Humanity's Last Exam | 47.45 | Accuracy (%) | 94.5 |
Interactive version: theaggregate.ai/model?slug=muse-spark-1-3-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-20.