Tech News
Meta Muse Wonder Full Matches Sonnet 5.5 on Artificial Analysis Benchmark
Meta’s new Muse Wonder Full model scores 56 on the Intelligence Index, matching Sonnet 5.5 and surpassing Fable 5.1 at maximum reasoning effort.
Artificial Analysis
Everything Threat Times has reported about Artificial Analysis: 2 stories, newest first. Part of our AI coverage.
AI
Mistral Large 4 Leads Non-Chinese Models in AI Benchmarks, Trails Chinese Peers
Independent tests show Mistral’s new Large 4 model outperforms Western rivals but lags behind several Chinese open models in overall intelligence scores.