Skip to content
Leaders Board.
Models/MetaClosed

Muse Spark 1.1

#15 of all models across the language-model boards, #1 on 1 board.
#15
Overall rank
14.0
Podium score
1
Board wins
Jul 9, 2026
Released
1Chat·Reasoning·Coding1Agents and tools·Vision

Chat

Which model people prefer in blind head-to-head conversations.

2
MultiChallenge
75.3% · of 29
as “Muse Spark 1.1”
9
Text Arena
1,493 · of 100
as “muse-spark-1.1”

Reasoning

Hard questions with checkable answers: science, math, puzzles, expert exams.

33
Epoch ECI
154.3 · of 100
as “Muse Spark 1.1”
33
LiveBench
75.3% · of 59
as “muse-spark-1.1-xhigh”

Coding

Fixing real repositories, building web apps, editing code.

28
WebDev Arena
1,542 · of 100
as “muse-spark-1.1”

Agents and tools

Calling functions and tools, using MCP servers, searching the web.

1
MCP Atlas
88.1% · of 34
as “Muse Spark 1.1”

Vision

Understanding images, charts and documents.

15
Document Arena
1,465 · of 38
as “muse-spark-1.1”
18
Vision Arena
1,281 · of 100
as “muse-spark-1.1”

More from Meta

Muse Spark 1.3Muse Spark 1.2Muse SparkMuse GlimmerLlama 4 Maverick 17b 128eLlama 4 Maverick InstructLlama 4 Scout InstructMetavoice V1

Scores as published by each board on the capture date. Model names and logos belong to their owners; logos via logo.dev.

Weekly: the AI leaderboards with a new #1, Saturday mornings.