GitHub[208K]Try OpenCode

Compare AI models: Dracarys Llama 3.1 70B Instruct vs Step 5 Preview

  1. Dracarys Llama 3.1 70B InstructAbacusaiHollow points use fallbacks · hover for details
  2. Step 5 PreviewStepFunHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Dracarys Llama 3.1 70B Instruct0/100 — Reasoning not supported50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder37/1000/1000/100 — Tool calling not supported
Step 5 Preview50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder37/10082/10050/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
131K
1M
Reasoning
False
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
Unknown
$1.00/ 1M
Output
Unknown
$2.70/ 1M
Cached input
Unknown
$0.05/ 1M
MomentumLast 2 mo
Unique users
No usage
113K
Completed sessions
No usage
2,627,845
Token share
No usage
0.64%
Tokens
No usage
7.2T+100%
No trend data
AUG 28OCT 22
RetentionWeek 1
Returning users
Pending
77.1%933 user-weeks

Related comparisons. Other model pairs to check.