GitHub[208K]Try OpenCode

Compare AI models: Kimi K2.6 vs Hy3

  1. Kimi K2.6MoonshotHollow points use fallbacks · hover for details
  2. Hy3Tencent
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2.650/100 — Reasoning supported; no comparable benchmark80/10036/10064/10050/10027/100
Hy367/10070/10068/10054/1000/10043/100
Overview
Author
Context length
262K
256K
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.74/ 1M
$0.16/ 1M
Output
$3.72/ 1M
$0.64/ 1M
Cached input
Unknown
$0.04/ 1M
MomentumLast 2 mo
Unique users
99K
290K
Completed sessions
229,791
6,020,405
Token share
0.02%
0.58%
Tokens
185B-78%
5.7T+311%
AUG 20OCT 14
AUG 20OCT 14
RetentionWeek 1
Returning users
62.7%3.9K user-weeks
71.5%3.4K user-weeks

Related comparisons. Other model pairs to check.