AI Trends

Arena.ai Evaluation Says Muse Ember Leads Comparable Models in Speed, Performance, and Cost

ArenaUpdated Nov 19 03:28

AI summary

According to an Arena.ai evaluation, Muse Ember (Max) outperforms GPT-6 Luna (Max) and Claude Haiku 5.5 (High) in speed, Agent Arena score, and cost. The three models took 27s, 5.8 min, and 1.9 min per task, respectively; achieved Net Improvement scores of +2.3%, +1.4%, and +0.4%; and cost 1.9¢, 7.0¢, and 6.9¢, respectively.

Why read this

AI score 54

These real-world tests compare models across speed, Agent Arena score, and per-task cost, helping assess efficiency trade-offs for actual workloads.

Topics

Tags

Body

The race among efficient models built for real work has a new leader: Muse Ember by @AIatMeta.

Ember (Max) leads on every dimension against GPT-6 Luna (Max) from @OpenAI and Claude Haiku 5.5 (High) by @AnthropicAI:

- Speed: 27s per task vs 5.8 min and 1.9 min - Performance: +2.3% Net Improvement (Agent Arena score) vs +1.4% and +0.4% - Cost: 1.9¢ per task vs 7.0¢ and 6.9¢

That’s ~13x faster than Luna and less than a third of the cost of either. Below find more analysis on Ember’s steerability score across Work, and a look at what real-world tasks users are shipping with Muse Ember in the Agent Arena.

Source

Arena