3 vs 0 benchmarks won
Meta Muse Spark | OpenAI GPT-5.1 | |
|---|---|---|
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Apr 8 2026 | Nov 12 2025 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 89.5% | 88.1% |
Software engineering SWE-Bench Verified | 77.4% | 76.3% |
Multimodal understanding MMMU | 80.4% | 76% |
| Timeline | ||
| Release gap | GPT-5.1 shipped 147 days before Muse Spark | |
Muse Spark leads GPT-5.1 on 3 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). GPT-5.1 shipped 147 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%, 1.4 points above GPT-5.1 at 88.1%. On SWE-Bench Verified, Muse Spark scores 77.4%, 1.1 points above GPT-5.1 at 76.3%. On MMMU, Muse Spark scores 80.4%, 4.4 points above GPT-5.1 at 76%.