‹ PublicAI Index
The LLM benchmark aggregator.
Muse Ember
Meta
Strongest in Legal (#4 of 173), weakest in Core abilities (#63 of 199). Above par in 10 of 10 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 4 Argon and Muse Wonder Full and ahead of O3 and O4 Mini.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Professional56.6−5.8#18/1941/2
Legal63.4−2.5#4/1731/1
Coding55.4−10.8#31/1791/6
Agentic coding55.9−11#31/1731/5
Reasoning55.4−10#41/1951/5
Reasoning58.6−10.4#27/1471/3
Agents55.9−10.5#48/2981/6
Knowledge work61.8−8.9#36/2081/2
Core abilities53.4−11.9#63/1991/4
General intelligence54.9−14.5#50/1781/3
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Muse Ember, left for the other.
§ 3 · Sources
Where the numbers come from
4 publications, 6 figures. Every one links to the page it was read from.
Artificial Analysis Intelligence Index 36
AA-Briefcase 1521
SimpleBench 72.7%
Vals · Legal Research Bench 49.04%Vals · Harvey Legal Agent Benchmark 25%Vals · Vibe Code Bench 83.7% (OpenHands)
Badge
[](https://publicai.io/model-index/m/muse-ember)