GitHub[220K]Try OpenCode

Compare AI models: Gemini 4 Argon vs Hy3

  1. Gemini 4 ArgonGoogleHollow points use fallbacks · hover for details
  2. Hy3Tencent
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Gemini 4 Argon50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder17/10093/10083/10050/100 — Tool calling supported; no comparable benchmark
Hy367/10068/10070/10053/1000/10040/100
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text, Image, Video, Audio, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$0.13/ 1M
Output
$10/ 1M
$0.53/ 1M
Cached input
$0.10/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
2.5K
77K
Completed sessions
8,598
567,367
Token share
0%
0.03%
Tokens
9.5B+100%
333B-95%
AUG 31OCT 25
AUG 31OCT 25
RetentionWeek 1
Returning users
Pending
70.1%2.9K user-weeks

Related comparisons. Other model pairs to check.