GitHub[208K]Try OpenCode

Compare AI models: DeepSeek V4 Flash vs Hy3 preview

  1. DeepSeek V4 FlashDeepSeek
  2. Hy3 previewTencentHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash26/10073/10053/10082/1000/1000/100
Hy3 preview50/100 — Reasoning supported; no comparable benchmark45/10069/10054/1000/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.44/ 1M
$0.17/ 1M
Output
$1.32/ 1M
$0.57/ 1M
Cached input
Unknown
$0.06/ 1M
MomentumLast 2 mo
Unique users
2.2M
0
Completed sessions
29,174,232
9,976
Token share
9.21%
0%
Tokens
104T-60%
0-100%
AUG 28OCT 22
No trend data
RetentionWeek 1
Returning users
67.2%194K user-weeks
Pending

Related comparisons. Other model pairs to check.