GitHub[220K]Try OpenCode

Compare AI models: DeepSeek V4 Pro vs flint-40b

  1. DeepSeek V4 ProDeepSeek
  2. flint-40bRecursiveHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/100100/10033/10081/1000/10068/100
flint-40b50/100 — 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
$1.60/ 1M
Unknown
Output
$3.20/ 1M
Unknown
Cached input
$0.14/ 1M
Unknown
MomentumLast 2 mo
Unique users
404K
45K
Completed sessions
1,453,749
484,937
Token share
0.43%
0.04%
Tokens
5.3T-82%
530B+100%
SEP 6OCT 31
SEP 6OCT 31
RetentionWeek 1
Returning users
55%36K user-weeks
Pending

Related comparisons. Other model pairs to check.