Muse Spark 1.2: benchmark results
Meta's Muse Spark 1.2 model, a coding-focused update to Muse Spark 1.1 released alongside the Muse Code terminal agent; API-only, with no disclosed parameter count. Provider: Meta. Released 2026-08-05. Access: API.
Unified ELO 1941 ± 9, rank #37 of 2650 rated models, from 106 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI Harvey Legal Agent Bench | 25.42 | Accuracy (%) | 100 |
| Dnotitia Korean LLM Leaderboard | 100 | Mean Item Score (%) | 99.8 |
| Design Arena (Data Viz) | 1365 | Elo | 99.4 |
| Vals AI Finance Agent v2 | 60.6 | Accuracy (%) | 98.3 |
| AI for Education SEND | 88.07 | Accuracy (%) | 98.1 |
| Appwrite Arena (With Skills) | 97.8 | Overall Score (%) | 97.8 |
| AI for Education Pedagogy - Maths | 94.44 | Accuracy (%) | 97.5 |
| BenchmarkList ECI | 148.45 | Capability Index (ECI) | 96.4 |
| Design Arena (Website) | 1321 | Elo | 96.3 |
| Design Arena (ASCII Art) | 1323 | Elo | 95.4 |
| Tinybird AI SQL Benchmark - Exactness | 57.22 | Result exactness vs human reference queries (0-100) | 95.1 |
| ChessBench - Coherence | 86 | Coherence (%) | 95 |
Interactive version: theaggregate.ai/model?slug=muse-spark-1-2 · How It Works · Data refreshed daily, snapshot 2026-09-20.