GitHub[208K]Try OpenCode

Compare AI models: DeepSeek V4 Pro vs mai-experimental-test

  1. DeepSeek V4 ProDeepSeek
  2. mai-experimental-testHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/100100/10037/10080/1000/10068/100
mai-experimental-test50/100 — 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
$1.74/ 1M
Unknown
Output
$3.48/ 1M
Unknown
Cached input
$0.20/ 1M
Unknown
MomentumLast 2 mo
Unique users
963K
56K
Completed sessions
1,453,630
585,872
Token share
1.88%
0.03%
Tokens
17T-42%
273B+100%
AUG 8OCT 2
AUG 8OCT 2
RetentionWeek 1
Returning users
56.1%92K user-weeks
Pending

Related comparisons. Other model pairs to check.