GitHub[225K]Try OpenCode

Compare AI models: MiniMax-M3 vs iceman

  1. MiniMax-M3MiniMaxHollow points use fallbacks · hover for details
  2. icemanHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
MiniMax-M350/100 — Reasoning supported; no comparable benchmark83/10060/10092/10050/10021/100
iceman50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder
Overview
Author
Context length
1M
Unknown
Reasoning
True
Unknown
Input modalities
Text, Image, Video
Unknown
Output modalities
Text
Unknown
Providers
Pricing
Input
$0.23/ 1M
Unknown
Output
$0.96/ 1M
Unknown
Cached input
$0.05/ 1M
Unknown
MomentumLast 2 mo
Unique users
179K
82K
Completed sessions
1,474,159
825,566
Token share
0.16%
0.2%
Tokens
2.1T-48%
2.6T+100%
SEP 11NOV 5
SEP 11NOV 5
RetentionWeek 1
Returning users
59.7%10K user-weeks
Pending

Related comparisons. Other model pairs to check.