GitHub[208K]Try OpenCode

CompareAI models

  1. Qwen3.6 PlusAlibabaHollow points use fallbacks · hover for details
  2. Kimi K2.6MoonshotHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.6 Plus50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder45/10080/10050/10050/100 — Tool calling supported; no comparable benchmark
Kimi K2.650/100 — Reasoning supported; no comparable benchmark80/10039/10061/10050/10027/100
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.50/ 1M
$0.74/ 1M
Output
$3.00/ 1M
$3.72/ 1M
Cached input
$0.05/ 1M
Unknown
MomentumLast 2 mo
Unique users
72K
161K
Completed sessions
114,346
225,658
Token share
0.02%
0.04%
Tokens
136B-61%
309B-73%
AUG 6SEP 30
AUG 6SEP 30
RetentionWeek 1
Returning users
54.3%2.8K user-weeks
55.9%6.4K user-weeks

Related comparisons. Other model pairs to check.