1 vs 2 benchmarks won
Anthropic Claude Opus 4.5 | Meta Muse Spark | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Nov 24 2025 | Apr 8 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 87% | 89.5% |
Software engineering SWE-Bench Verified | 80.9% | 77.4% |
Multimodal understanding MMMU | — | 80.4% |
| Timeline | ||
| Release gap | Claude Opus 4.5 shipped 135 days before Muse Spark | |
Muse Spark leads Claude Opus 4.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Opus 4.5 shipped 135 days before Muse Spark, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, Muse Spark scores 89.5%, 2.5 points above Claude Opus 4.5 at 87%. On SWE-Bench Verified, Claude Opus 4.5 scores 80.9%, 3.5 points above Muse Spark at 77.4%.