Skip to content
View original post on X: Arena.aiOfficial
Published
55/100

Arena ranks Meta's Muse Ember as the most efficient model in Agent Arena

AIArena reports that Meta's Muse Ember (Max) leads Agent Arena on cost-efficiency, with a +1.7% net improvement at about $0.02 per task across 6k real-world agentic sessions. Arena says it is roughly 4x cheaper per task than GPT-6 Luna (Max) and Claude Haiku 5.5, with performance on par across the three.
Arena.aiVerified on XOfficial
@arena
View on X

Muse Ember (Max) by @AIatMeta lands in Agent Arena as the most capable and efficient : +1.7% net improvement at about $0.02 per task, roughly 4x less than GPT-6 Luna (Max) and Claude Haiku 5.5, across 6k real-world agentic sessions from our global community.

How it stacks up against other efficient models
- #25 Muse Ember (Max): +1.7% | $0.02/task | 0.5 min/task | 11.6K output tokens
- #26 GPT-6 Luna (Max): +1.6% | $0.09/task | 6 min/task | 41.2K output tokens
- #29 Claude Haiku 5.5 (High): +0.5% | $0.08/task | 1.8 min/task | 24.3K output tokens

Performance is on par across the three, but Ember's median task costs roughly 4x less, finishes about 12x faster than Luna (Max) and 3.5x faster than Haiku 5.5, and uses 72% and 52% fewer output tokens.

Congrats to the @AIatMeta team, @alexandr_wang and @finkd on this impressive release!

AI at Meta@AIatMeta
Today we're introducing Muse Ember, our smallest and most efficient model, built for complex reasoning execution and everyday agent work. Muse Ember can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes. With a 1M-token context window and native understanding of text, images, audio and video, it can also work across large document sets and varied inputs.
View quoted post on X
Source details

Arena.ai · x.comPublished · added here

Original title: Muse Ember (Max) by @AIatMeta lands in Agent Arena as the most capable and efficient : +1.7% net improvement at about $0.02 per task, rou...

Topics

AI agentsEvals & benchmarks