Meta Muse Ember (Max) tops Code Arena WebDev small-model ranking at 1608 pts
The benchmark gap over Haiku 5.5 and GPT-6 Luna is modest in points but wide in cost per completed task, which matters most for teams running high-volume codegen. Developers building website or app scaffolding pipelines can test Ember against Haiku on their own workloads to validate the claimed 2x cost advantage at equal API rates. Volume API buyers should watch whether actual task-level cost, not sticker pricing, becomes the new battleground for small coding models.
Meta (@AIatMeta) has placed Muse Ember (Max) on the Code Arena: WebDev leaderboard, where it debuts as the highest-performing small model with a score of 1608 points. It outranks two leading small models: Anthropic's Claude Haiku 5.5 (High) at 1595 points (#35) and OpenAI's GPT-6 Luna (Max) at 1578 points (#42).
All three models share identical API pricing of US$0.10/US$0.50 per million input/output tokens, yet Ember's median cost per task is about US$0.03, versus US$0.06 for Luna and US$0.11 for Haiku, roughly 2x and 3.7x cheaper respectively. That combination of score and cost places Ember on the Pareto frontier, where neither Haiku nor Luna lands. Arena.ai's own testing saw Ember generate 25 complex website and animation tasks at an average of about 2 minutes per task, totalling roughly US$1.
The result signals that small models are closing the real-world web-development gap with larger systems, with Meta positioning Ember for fast, high-quality, low-cost coding workloads.
Muse Ember (Max) from @AIatMeta just landed in the Code Arena: WebDev as the highest-performing small model - built for fast, high-quality, low-cost work. Watch the video below: 20+ websites and animations, all generated by Ember in one go. Across the generations we timed, the average was about 2 minutes and about $0.04 per task.
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Meta, Muse Ember, Claude Haiku 5.5, GPT-6 Luna.
Source attribution: curated from lmarena.ai (@lmarena_ai).
