Understand this story
Story summary
The English summary is being updated. See the reporting timeline below.
Latest development · Report
Arena.ai Evaluation Says Muse Ember Leads Comparable Models in Speed, Performance, and CostDevelopments
1 confirmed developments
- Source:Arena
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 18
Arena
Arena.ai Evaluation Says Muse Ember Leads Comparable Models in Speed, Performance, and Cost
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.
AI Trends