Meta's new frontier model Muse Wonder Full breaks into the AI top tier
Quick Answer
Meta's Muse Wonder Full and Muse Wonder models achieve top-tier AI performance, scoring 56 and 52 points respectively on the Artificial Analysis Intelligence Index.
Quick Take
Significant improvements in coding and agentic evaluations are noted, although factual knowledge lags behind competitors. Pricing has increased substantially, with Muse Wonder costing $4.52 per task.
Key Points
- Muse Wonder Full scores 56 points, ranking among the top frontier models.
- Significant coding improvements: Muse Wonder Full scores 68 on the Coding Agents Index.
- Factual knowledge remains a weakness, with Muse Wonder Full scoring only 30 points.
- Muse Wonder costs $4.52 per task, nearly three times more than its predecessor.
- Meta claims improved performance on unfamiliar tasks due to a stronger base model.
DeepSignal Analysis
What happened
Meta has introduced its new AI models, Muse Wonder Full and Muse Wonder, which have achieved high scores on the Artificial Analysis Intelligence Index, with 56 and 52 points respectively. These models show significant improvements in coding capabilities but lag in factual knowledge compared to competitors. The pricing for Muse Wonder has increased to $4.52 per task, reflecting a substantial rise from its predecessor.
Key evidence
- Muse Wonder Full scored 56 points on the Artificial Analysis Intelligence Index v4.3, while Muse Wonder scored 52, marking a notable improvement from the previous Muse Spark 1.3's score of 48.
- On the Coding Agents Index, Muse Wonder Full achieved 68 points, tying with Claude Code, while Muse Wonder scored 63, up from 54 for its predecessor.
- The cost for using Muse Wonder is $4.52 per task, nearly three times more than Muse Spark 1.3, which was priced at $1.60.
Why it matters
The advancements in Meta's Muse models indicate a recovery in their AI capabilities, particularly in coding and agentic evaluations, which are crucial for complex task handling. However, the lower factual knowledge scores suggest that while Meta is improving its models, they may still not match the comprehensive knowledge bases of leading competitors. The increased pricing could impact adoption rates, especially among users sensitive to cost.
📖 Reader Mode
~3 min readMeta 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 v4.3, while Muse Wonder hits 52. Its predecessor, Muse Spark 1.3, 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 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 and Muse Code, while Muse Wonder Full is currently limited to Muse Code users. Muse Wonder will soon power the Muse app 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) hallucinates less often.
Meta addresses a common criticism in its blog post, 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, 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.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
