Meta's Muse Wonder Full model scores 56 on AI index, closing gap with top models
meta released two new ai models, muse wonder and muse wonder full, with significant gains in agentic coding and autonomous problem-solving, scoring 56 and 52 on artificial analysis intelligence index v4.3, respectively.
meta has released two new ai models, muse wonder and muse wonder full, which have scored 52 and 56 on the artificial analysis intelligence index v4.3, respectively. the models demonstrate significant gains in agentic evaluations, particularly in coding and autonomous problem-solving, with muse wonder full achieving 57 percent on terminal-bench 4.0, up from 33 percent for its predecessor, muse spark 1.3. both models support a one-million-token context window and accept text, images, video, and audio as input. muse wonder full ties with claude code with sonnet 5.5 on the coding agents index with a score of 68.