- Intelligence
- 6.5
- Rank 607 of 744 measured models
- Coding
- 8.2
- Rank 278 of 298 measured models
- Output speed
- 67.6 t/s
- Rank 256 of 403 measured models
- Price/1M
- $0.30
- Rank 206 of 659 measured models
- Context window
- 10M
- Rank 4 of 1199 measured models
- Cost per task
- $0.112
- Rank 55 of 193 measured models
Llama 4 Scout scores 6.5 on the Artificial Analysis Intelligence Index, ranking 607th of 744 measured models. The closest models on this index are DeepSeek R1 Distill Llama 8B (6.5), Mistral Saba (6.5), and Olmo 3 32B Think (6.5).
Additional benchmarks5
Design Arena · Codecategories26.6%
Design Arena · Dataviz39.3%
Design Arena · Gamedev27.4%
Design Arena · Uicomponent25.5%
Design Arena · Website22.7%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek-V2.5
DeepSeek · — · —
6.6+0.1——Compare - DeepSeek R1 Distill Llama 8B
DeepSeek · — · —
6.5——Compare - Mistral Saba
Mistral · — · —
6.5——Compare - Olmo 3 32B Think
Allen Institute for AI · — · —
6.5——Compare
