GitHub[220K]Try OpenCode

Compare AI models: test vs Gemini 3.8 Flash

  1. testDeepSeekHollow points use fallbacks · hover for details
  2. Gemini 3.8 FlashGoogle
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
test50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder
Gemini 3.8 Flash50/10081/10032/10093/10083/10050/100
Overview
Author
Context length
Unknown
1M
Reasoning
Unknown
True
Input modalities
Unknown
Text, Image, Video, Audio, Pdf
Output modalities
Unknown
Text
Providers
Pricing
Input
Unknown
$0.75/ 1M
Output
Unknown
$3.75/ 1M
Cached input
Unknown
$0.07/ 1M
MomentumLast 2 mo
Unique users
942
1
Completed sessions
10,068
17
Token share
0%
0%
Tokens
4.4B+100%
73K+100%
AUG 29OCT 23
AUG 29OCT 23
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.