GitHub[220K]Try OpenCode

Compare AI models: DeepSeek V4 Pro vs iceman

  1. DeepSeek V4 ProDeepSeek
  2. icemanHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/100100/10031/10081/1000/10068/100
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
Unknown
Output modalities
Text
Unknown
Providers
Pricing
Input
$1.75/ 1M
Unknown
Output
$3.50/ 1M
Unknown
Cached input
$0.44/ 1M
Unknown
MomentumLast 2 mo
Unique users
396K
77K
Completed sessions
1,468,694
797,367
Token share
0.42%
0.2%
Tokens
5.4T-80%
2.5T+100%
SEP 9NOV 3
SEP 9NOV 3
RetentionWeek 1
Returning users
56%30K user-weeks
Pending

Related comparisons. Other model pairs to check.