Unverified50% confidenceBenchmarkExact time
Among the 11 benchmarks officially published, the terminal operation test version 4.0 rose from 31.2 to 42.3, the deep software engineering test version 1.1 rose from 74.2 to 77.0, the automation test reached 60.5, and the Agent ultimate exam scored 35.4.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/21/2026
First Seen
Valid until: 11/4/2026
Sources
Related Entities
Related Claims
UnverifiedIn the 16 benchmarks officially published for 2.5-24, it scored 27.69 on automated tasks, with second place at 8.72, leading by about 3.2 times.74% similarUnverifiedGLM-5.3在六项评测中的成绩为：终端编程基准3.0得28.3、深度软件工程基准得66.9、智能体中场考试得28.5、自动化基准得48.2、带工具的人类终极考试得62.5、GDP价值评估AA2版得17.6970% similarUnverifiedThe current version of WarderBox is v0.3.5, containing 42 modules and 390 tests.69% similarUnverifiedDeepSeek V4.1 claims to achieve 74 on SWE, but the blogger found that this was the best result cherry-picked from multiple tests, with open code testing at 65 and PI testing at 66.67% similarUnverifiedIndependent testing shows Mistral Large 4 achieved a success rate of 81.7% on the CyberGym E2E end-to-end test, the highest among 18 tested models.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1083437API
curl https://kongchang.com/api/v1/knowledge/claims/1083437MCP
get_claim(id=1083437)