DeepSeek’s long-awaited flagship V4 model has fallen short of its domestic and US rivals, according to a new analysis, as the Chinese artificial intelligence firm struggles to replicate the market-shaking success of its earlier R1 release.The company’s most advanced system, V4 Pro, ranked second among the world’s leading open-source models, behind Beijing-based Moonshot AI’s Kimi K2.6, benchmark firm Artificial Analysis said in a report on Friday.While V4 Pro marked a clear improvement on its predecessor, V3.2, it still lagged top competitors.
SRCSouth China Morning Post
LANGEN
LEANCenter-Right
WORDS81
ENT10
SAT · 2026-04-25 · 08:51 GMTBRIEF NSR-2026-0425-71607
NSR-2026-0425-71607News Report·EN·Technology
Underwhelming or underrated? DeepSeek V4 shows “impressive” gains
DeepSeek's new flagship AI model, V4 Pro, has been analyzed and found to be underwhelming compared to its domestic and US competitors. A report by Artificial Analysis on Friday stated that V4 Pro ranked second among leading open-source models, trailing behind Moonshot AI's Kimi K2.6.
Xinmei ShenSouth China Morning PostFiled 2026-04-25 · 08:51 GMTLean · Center-RightRead · 1 min
South China Morning PostFIG 01
Reading time
1min
Word count
81words
Sources cited
1cited
Entities identified
10entities
Quality score
100%
§ 01
Briefing Summary
AI-generatedNEWSAR · AI
DeepSeek's new flagship AI model, V4 Pro, has been analyzed and found to be underwhelming compared to its domestic and US competitors. A report by Artificial Analysis on Friday stated that V4 Pro ranked second among leading open-source models, trailing behind Moonshot AI's Kimi K2.6. While V4 Pro represents an improvement over its predecessor, V3.2, it did not achieve the market impact of DeepSeek's earlier R1 release. This analysis highlights DeepSeek's ongoing challenge in replicating the success of its previous models with its latest offering.
Confidence 0.85Sources 1Claims 4Entities 10
§ 02
Article analysis
Model · rule-basedFraming
Technology
Economic Impact
Tone
Measured
AI-assessed
CalmNeutralAlarmist
Factuality
0.70 / 1.00
Factual
LowHigh
Sources cited
1
Limited
FewMany
§ 03
Key claims
4 extracted01
Kimi K2.6 is ahead of DeepSeek V4 Pro.
factualArtificial Analysis
Confidence
1.00
02
V4 Pro ranked second among the world’s leading open-source models.
factualArtificial Analysis
Confidence
1.00
03
DeepSeek V4 has fallen short of its domestic and US rivals.
factualnull
Confidence
0.90
04
V4 Pro marked a clear improvement on its predecessor, V3.2.
factualnull
Confidence
0.80
§ 04
Full report
1 min read · 81 words§ 05
Entities
10 identifiedKey playerOppositionContextPositiveNeutralNegative
Organizations7
§ 06
Keywords & salience
8 termsdeepseek v4
1.00
artificial intelligence
0.90
open-source models
0.80
ai model performance
0.70
deepseek v3.2
0.60
kimi k2.6
0.50
moonshot ai
0.50
benchmark analysis
0.40
§ 07
Topic connections
Interactive graph Network visualization showing 16 related topics
View Full Graph Person Organization Location Event|Click node to navigate|Edge numbers = shared articles