muse-spark
89.8%±2.2%
87.6%CI92.0%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 30 min30 minutes ago
All sources syncing normally
- Arena · Text· 7 hours ago
- Arena · WebDev· 7 hours ago
- Arena · Vision· 7 hours ago
- Arena · Agent· 7 hours ago
- GPQA Diamond· 30 minutes ago
- SWE-bench· 30 minutes ago
- Terminal-Bench· 30 minutes ago
- ARC-AGI-2· 30 minutes ago
Filter by org:
Released:
Muse-Spark-Open-816B-A42B
88.6%±1.9%
86.7%CI90.4%
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 45 | muse-spark | Meta AI | Sep 2026 | — | 89.8% | 87.6%–92.0% | #16–40 | ||
| 50 | Muse-Spark-Open-816B-A42B | Meta AI | — | — | 88.6% | 86.7%–90.4% | #54–119 |
Showing GPQA Diamond exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.