GitHub[220K]Try OpenCode

Compare AI models: LongCat-2.5-Preview vs iceman

  1. LongCat-2.5-PreviewMeituanHollow 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
LongCat-2.5-Preview50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder38/10081/10033/10050/100 — Tool calling supported; no comparable benchmark
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
Unknown
Output modalities
Text
Unknown
Providers
Pricing
Input
$0.75/ 1M
Unknown
Output
$2.95/ 1M
Unknown
Cached input
$0.01/ 1M
Unknown
MomentumLast 2 mo
Unique users
291K
25K
Completed sessions
15,849,760
280,058
Token share
0.76%
0.07%
Tokens
9T+100%
841B+100%
SEP 1OCT 26
SEP 1OCT 26
RetentionWeek 1
Returning users
62.6%2.8K user-weeks
Pending

Related comparisons. Other model pairs to check.