Unverified50% confidenceBenchmarkExact time
According to Artificial Analysis leaderboard data, DeepSeek V4 Pro's score increased from 52 to 53, a difference of only 1 point.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/30/2026
First Seen
Valid until: 11/28/2026
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4 Pro's floating-point operations have been reduced to 27% of the V3.2 version (a 3.7x reduction).69% similarUnverifiedDeepSeek V4 Pro leads Qwen3.6 27B Q4 by approximately 6%, and if it had not unexpectedly underperformed on the reasoning-mathematics items, the lead could have exceeded 10%.68% similarUnverifiedQwen3 27B is in the same tier as the DeepSeek V-Flash series on the overall intelligence leaderboard, with scores in the 52–53 range.66% similarUnverifiedOn the DeepSWE benchmark, GPT-5.6 scored 45 at Low, 61 at Medium, 69 at High, 71 at X-High, and 73 at Max across reasoning tiers.66% similarUnverifiedDeepSeek V4 Pro scored 37.7 on the Humanity's Last Exam benchmark.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/823948API
curl https://kongchang.com/api/v1/knowledge/claims/823948MCP
get_claim(id=823948)