Unverified50% confidenceBenchmarkExact time
When a third party tested the September version using the strictest 'Fully' criterion, the Program Bench pass rate was only 0.5%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
DeepSeek V4.1 Flash Update: The Parameter Truth, Benchmark Controversy, and Cost Revolution
bilibiliAI技术投降派10/18/2026
Related Entities
Related Claims
UnverifiedThe Program Bench score rose from 20.3 to 29.1, an improvement of 8.8 points, using the 'Almost' criterion (passing 5 of 9 tests counts as a pass).68% similarUnverifiedCaveman's fixed benchmark test results from 54 runs show a 33.2% reduction in input tokens, with all 18/18 correctness checks passing.63% similarUnverifiedIn DeepSeek's official comparison, when running with the same checkpoint at best effort, its minimal framework scored 72.6 while the open-source code scored 65.5.62% similarUnverifiedIn a 20-document setting, GPT-3.5-Turbo's correct answer rate is approximately 75.8% when the relevant passage is ranked first, approximately 63.2% when ranked last, and only 53.8% when placed in the middle, while the closed-book score without any documents is 56.1%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059808API
curl https://kongchang.com/api/v1/knowledge/claims/1059808MCP
get_claim(id=1059808)