Llama 4 Scout
Meta
MaverickOpen weights- Intelligence8.1
- Hallucination79%
- Context10M
- KnowledgeAug 2024
- Speed73tok/s
- Response7.7s
- Price$0.30
- Modalities3
Llama 4 Scout
Meta · Odd ones out, each with one stat no other card can match.
Card stats
Intelligence ▲ higher wins
Intelligence Index: a composite score from 10 hard evaluations covering reasoning, knowledge, coding, agents and science.
8.1
beats 0% of deck
Hallucination ▼ lower wins
Hallucination rate: of the questions a model gets wrong, how often it confidently makes up an answer instead of saying it doesn't know. Lower wins.
79 %
beats 26% of deck
Context ▲ higher wins
Context window: how many tokens of input the model can consider at once.
10M
beats 100% of deck
Knowledge ▲ higher wins
Training-data cutoff: the most recent month the model learned about. Later wins. N/D means the lab hasn't disclosed it, and an N/D card loses this stat.
Aug 2024
beats 42% of deck
Speed ▲ higher wins
Median output speed in tokens per second, measured on the labs' own APIs.
73 tok/s
beats 26% of deck
Response ▼ lower wins
End-to-end response time: seconds to receive a 500-token answer, thinking time included. Lower wins.
7.7 s
beats 94% of deck
Price ▼ lower wins
Blended price per million tokens (3:1 input to output). Lower wins.
$0.30
beats 81% of deck
Modalities ▲ higher wins
Number of supported input and output modalities: text, image, audio and video.
3
beats 45% of deck
Model facts
- Released
- 2025-04-05
- Weights
- Open · LLAMA 4 COMMUNITY LICENSE AGREEMENT
- Parameters
- 109B (17B active)
- Reasoning
- No
- Price in / out
- $0.18 / $0.66 per 1M
- Time to first token
- 0.83 s
- Humanity’s Last Exam
- 3.8%
- GPQA Diamond
- 58.7%
- SciCode
- 21.3%