2 vs 1 benchmarks won
Anthropic Claude Sonnet 4.6 | Meta Muse Spark | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Feb 17 2026 | Apr 8 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 89.9% | 89.5% |
Software engineering SWE-Bench Verified | 79.6% | 77.4% |
Multimodal understanding MMMU | — | 80.4% |
| Timeline | ||
| Release gap | Claude Sonnet 4.6 shipped 50 days before Muse Spark | |
Claude Sonnet 4.6 leads Muse Spark on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Sonnet 4.6 shipped 50 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, Claude Sonnet 4.6 scores 89.9%, 0.4 points above Muse Spark at 89.5%. On SWE-Bench Verified, Claude Sonnet 4.6 scores 79.6%, 2.2 points above Muse Spark at 77.4%.