Unverified50% confidenceBenchmarkExact time
The 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).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
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
UnverifiedIn the Automation Bench test, the score improved from Cell's 8.1 to Astra's 41.4, and the CAD task score improved from 83.3 to 95.9.70% similarUnverifiedWhen a third party tested the September version using the strictest 'Fully' criterion, the Program Bench pass rate was only 0.5%.68% similarUnverified在 Terminal Bench 2.1 测试中，AutoPrompt Scale 使 OpenCode 在 89 个任务中的失败数从 29 降到 16，多解决 13 题，分数提升 14.61 个百分点67% similarUnverifiedIn the Automation Bench test, GPT-6 Sol's extra high tier achieved first place 33% of the time, while 5.6's max effort scored 28.8.67% similarUnverifiedOn Terminal Bench, Fable 5.1's score is approximately 20 points higher than Grok 4.7's, representing close to a 50% improvement.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059802API
curl https://kongchang.com/api/v1/knowledge/claims/1059802MCP
get_claim(id=1059802)