Muse Wonder (high) scores 93.4 on the Extended NYT Connections Benchmark, ahead of Muse Spark 1.3 (high) at 85.1. It's among the most expensive models tested.
Summary
Muse Wonder (high) achieves 93.4 on the Extended NYT Connections Benchmark, surpassing Muse Spark 1.3 (high) at 85.1, though it ranks among the most expensive models tested.
Similar Articles
Muse Wonder (high) scores 1.96 on the Short Story Creative Writing Benchmark, compared with 0.56 for Muse Spark 1.3 (high). Gemini 4 Argon (high) scores 0.80, up from −2.17 for Gemini 3.1 Pro Preview.
Gemini 4 Argon dramatically outperforms Gemini 3.1 Pro Preview on a creative writing benchmark (0.80 vs -2.17), winning all 50 matched story comparisons, while Muse Wonder scores 1.96 versus 0.56 for Muse Spark 1.3. The leaderboard covers 59 writer models with over 110,000 judgments from cross-family judges.
Muse Spark 1.3
Muse Spark releases version 1.3, likely introducing enhancements or new features in its AI or software toolset.
Meta Muse Wonder: pricing, benchmarks and limits - MACCUS
Meta released Muse Wonder and Muse Wonder Full, its most capable AI models yet, designed for personal and professional agents, available via the Meta Model API and Muse Code subscriptions. The article details pricing ($4/$20 per million tokens), benchmarks versus Claude Opus 5.5, and limits like Contributor mode and restricted availability of the Full variant.
Muse spark 1.1 has been released with the lowest cost.
Muse spark 1.1 has been released, emphasizing the lowest cost, likely aiming for efficiency and affordability.
Muse Wonder 1.0 Benchmarks
Meta's Muse Wonder 1.0, described as a Fable Class Model, is benchmarked in a shared comparison chart.