GitHub[208K]Try OpenCode

Compare AI models: Dracarys Llama 3.1 70B Instruct vs Gemini 3.8 Flash

  1. Dracarys Llama 3.1 70B InstructAbacusaiHollow points use fallbacks · hover for details
  2. Gemini 3.8 FlashGoogle
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 placeholder100/10037/1000/1000/100 — Tool calling not supported
Gemini 3.8 Flash50/10081/10033/10093/10083/10050/100
Overview
Author
Context length
131K
1M
Reasoning
False
True
Input modalities
Text
Text, Image, Video, Audio, Pdf
Output modalities
Text
Text
Providers
Pricing
Input
$0.00/ 1M
$0.75/ 1M
Output
$0.00/ 1M
$3.75/ 1M
Cached input
Unknown
$0.07/ 1M
MomentumLast 2 mo
Unique users
No usage
1
Completed sessions
No usage
17
Token share
No usage
0%
Tokens
No usage
73K+100%
No trend data
AUG 27OCT 21
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.