Unverified50% confidenceBenchmarkExact time
Argon achieved a score of 77.9% on the DeepSWE benchmark, setting a new record
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/1/2026
First Seen
Valid until: 12/30/2026
Sources
Related Entities
Related Claims
UnverifiedArgon set a new record of 77.9% on DeepSWE v1.1, which measures real long-horizon software engineering tasks.77% similarUnverifiedDeepSeek的编程智能体DeepSWE在SWE-bench基准测试中从预览版的12.8分提升至62.7分62% similarUnverifiedCurrently, more than 70% of DeepSeek's computing power is used for training, with inference accounting for less than 30%.57% similarUnverifiedDeepSeek officially announced that V4 Pro scored as high as 87.9 on the Terminal Bench benchmark.56% similarUnverifiedDeepSeek Math V2 在 Putnam 数学竞赛中斩获118分（满分120）56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963904API
curl https://kongchang.com/api/v1/knowledge/claims/963904MCP
get_claim(id=963904)