Meta's new frontier model Muse Wonder Full breaks into the AI top tier

Meta released its frontier model Muse Wonder in two variants, with Muse Wonder Full scoring 56 points and Muse Wonder 52 on the Artificial Analysis Intelligence Index v4.3, up from 48 for predecessor Muse Spark 1.3. Both models support a one-million-token context window and text, image, video and audio input, with agentic performance on Terminal-Bench 4.0 jumping from 33 to 57 percent, though factual knowledge lags at 30 and 25 points on AA-Omniscience versus 46 for Claude Opus 5.5. Muse Wonder is available through Meta's API and Muse Code while Muse Wonder Full is limited to Muse Code users, and both cost nearly three times as much per API call as Muse Spark 1.3.

Meta's new frontier model Muse Wonder Full breaks into the AI top tier Key Points - Meta's two new models, Muse Wonder and Muse Wonder Full, close the gap to the leading frontier models. - The biggest gains are in agentic coding and autonomous problem-solving. - Both versions cost nearly three times as much per API call as their predecessor, Muse Spark 1.3. Meta released its frontier model Muse Wonder in two variants, and both land among the best AI models available. Muse Wonder Full scores 56 points on the Artificial Analysis Intelligence Index https://artificialanalysis.ai/models/muse-wonder-full v4.3, while Muse Wonder hits 52. Its predecessor, Muse Spark 1.3 https://the-decoder.com/meta-closes-in-on-the-top-with-muse-spark-1-3-and-undercuts-rivals-on-price/ , sat at 48 points, which makes this a significant jump from what was a mid-tier model. The biggest gains show up in agentic evaluations, tests that measure how well an AI model can handle complex tasks on its own. On Terminal-Bench 4.0, performance jumped from 33 to 57 percent. Muse Wonder Full places in the top three on six out of ten benchmarks overall, a strong result for Meta, which seems to have recovered after a weaker stretch with its open Llama models. Meta highlights two new features. "Active Memory" lets the model remember key information across conversations and recall it when needed. "Active Focus" is the model's ability to stick with difficult tasks, try alternative approaches, and ask follow-up questions when something isn't clear. Both are central to Meta's pitch https://research.meta.ai/blog/muse-wonder for a personal AI agent that can access calendars, messages, and documents. Both models support a one-million-token context window and accept text, images, video, and audio as input. Muse Wonder is available through Meta's API https://dev.meta.ai/ and Muse Code https://dev.meta.ai/code , while Muse Wonder Full is currently limited to Muse Code users. Muse Wonder will soon power the Muse app https://muse.ai/ as well, starting with paying subscribers. Over time, Meta plans to build specialized models from it for all users. Coding jumps sharply, but factual knowledge lags behind Both models show big improvements in coding. Muse Wonder Full hits 68 points on the Coding Agents Index, tying Claude Code with Sonnet 5.5. Muse Wonder scores 63, up from 54 for its predecessor. Factual knowledge remains a weak spot. On the AA-Omniscience knowledge test, Muse Wonder Full manages only 30 points, and Muse Wonder gets 25. That's well behind Claude Opus 5.5 46 , GPT-6 Astra 43 , and Gemini 4 Argon 42 , which suggests the Wonder series is built on a smaller base model than its competitors. Low hallucination rates help offset this gap. Muse Wonder Full cuts its hallucination rate from 33 to 23 percent compared to its predecessor, the second-lowest among all models scoring at least 45 index points. Only Gemini 4 Argon 15 percent https://the-decoder.de/google-gemini-4-argon-schliesst-zur-ki-spitze-auf-bleibt-aber-hinter-anthropics-claude-opus-5-5/ hallucinates less often. Meta addresses a common criticism in its blog post https://research.meta.ai/blog/muse-wonder , that Muse models are tuned for benchmarks but fall short in real-world use. The company says Muse Wonder Full does better than expected on unfamiliar tasks that weren't part of training optimization, and credits this to a stronger base model. On the Vals AI Index https://x.com/ValsAI/status/2109706320383545474 , Muse Wonder Full Max debuts at fifth place and beats all OpenAI models, according to Vals AI. Only current Anthropic models score higher. Muse Wonder lands at tenth. The biggest improvements come from coding and math. On ProofBench, a private benchmark for mathematical proofs, Muse Wonder Full solves 94 out of 100 problems, up from 58 for its predecessor. That puts it just five to six points behind the top models 99 to 100 . On Terminal-Bench 4, Muse Wonder Full doubled its score while using 30 percent fewer output tokens. Performance on finance and legal tasks stayed at predecessor levels, dropping up to two points. Better performance comes at a steep price According to Artificial Analysis, Muse Wonder runs $4.52 per task on the Intelligence Index, nearly three times more than Muse Spark 1.3 $1.60 . Token pricing has climbed too, with $4 per million input tokens and $20 for output, up from $1.25 and $4.25 for the predecessor. Muse Wonder also uses 28 percent more input tokens per task, and those account for 76 percent of total costs. That puts Muse Wonder below Claude Fable 5.1 $7.63 and Claude Opus 5.5 $5.98 in pricing, but above GPT-6 Astra $3.26 , Gemini 4 Argon $1.99 , and GPT-6.1 Sol $0.72 . No token pricing is available yet for Muse Wonder Full. Both models do use about 10 percent fewer output tokens than their predecessor. Meta says it trained the models at its in-house Prometheus data center at gigawatt scale. More details are in the model card https://research.meta.ai/static/muse-wonder-model-card . AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now Meta https://research.meta.ai/blog/muse-wonder | Artificial Analysis https://artificialanalysis.ai/models/muse-wonder-full | Model Card https://research.meta.ai/static/muse-wonder-model-card