#17
Muse Spark 1.3
muse-spark-1.3
0.0
Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 98 tok/s
Overall Assistant Score
An average score combining the 5 main categories.
91.20 pts
Rank #17
84th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Muse Spark 1.3 is Meta's September 2, 2026 Spark—1M context, $1.25/$4.25. Rank looks high because it is benchmaxxed: tuned to crush short evals, not to hold a long assistant run. Helpfulness, instruction following, and comprehension look strong on one-shot work. Give it hours of tools and it drifts. We timed it ourselves, and it is much faster than Artificial Analysis reports. Empathy is cooler. Creative writing still pays a thinking tax: usable drafts, not literary. Use it for a sharp first answer, not a days-long assistant.

Overall Score vs Price

Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better

Ringed point is this model

Anthropic
Baidu
Bytedance
DeepSeek
Google
Meta
Minimax
Mistral
Moonshot
OpenAI
Qwen
SpaceX AI
Tencent
Xiaomi
Zhipu AI

Compare this model

Intelligence

Overall Score · Higher is better

chatio

The benchmark for real-world helpfulness. Evaluating LLMs on practical, everyday tasks that provide a clear picture of their real-world capabilities.

Designed and developed by Alex Tyh Wang

© Chatio 2026. All rights reserved.