GitHub[208K]Try OpenCode

CompareAI models

  1. Muse Spark 1.3 ContributorMeta
  2. Kimi K2.5MoonshotHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Muse Spark 1.3 Contributor100/100100/10084/10092/10083/100100/100
Kimi K2.550/100 — Reasoning supported; no comparable benchmark20/10046/10061/10050/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text, Image, Video, Pdf, Audio
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.10/ 1M
$0.45/ 1M
Output
$0.20/ 1M
$2.80/ 1M
Cached input
$0.002/ 1M
Unknown
MomentumLast 2 mo
Unique users
908K
37K
Completed sessions
289,602,727
14,807
Token share
16%
0%
Tokens
138T+100%
19B-72%
AUG 6SEP 30
AUG 6SEP 30
RetentionWeek 1
Returning users
67.5%24K user-weeks
62.8%557 user-weeks

Related comparisons. Other model pairs to check.