#95
Llama 4 Scout
llama-4-scout-17b-16e-instruct-fp8Helpfulness
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 97 tok/s
Overall Assistant Score
An average score combining the 5 main categories.
75.08 pts
Rank #95
8th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Llama 4 Scout is the efficiency-focused sibling in the Llama 4 family, featuring a 17B parameter Mixture-of-Experts architecture with 16 experts. Optimized for single-GPU deployment, it delivers remarkable multimodal performance and instruction following capabilities that rival much larger models. While slightly less nuanced than the Maverick variant, Scout offers an exceptional balance of speed, cost-effectiveness, and reasoning power, making it an ideal choice for high-throughput applications requiring reliable text and image understanding.
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
Speed
Output tokens per second · Higher is better
Price
USD per 1M input tokens · Lower is better
Meta Models
Overall Score · Same provider
Llama Family
Overall Score · Same model family
Closest Rivals
Overall Score · Nearest by overall rank