GitHub[208K]Try OpenCode

Compare AI models: Llama 4 Maverick 17B Instruct vs Step 3.7 Flash

  1. Llama 4 Maverick 17B InstructMetaHollow points use fallbacks · hover for details
  2. Step 3.7 FlashStepFun
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Llama 4 Maverick 17B Instruct0/100 — Reasoning not supported13/10065/10082/10033/10050/100 — Tool calling supported; no comparable benchmark
Step 3.7 Flash32/10096/10063/10054/10050/10055/100
Overview
Author
Context length
1M
256K
Reasoning
False
True
Input modalities
Text, Image
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.27/ 1M
$0.18/ 1M
Output
$0.85/ 1M
$1.11/ 1M
Cached input
Unknown
$0.04/ 1M
MomentumLast 2 mo
Unique users
No usage
No usage
Completed sessions
No usage
No usage
Token share
No usage
No usage
Tokens
No usage
No usage
No trend data
No trend data
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.