Unverified50% confidenceBenchmarkExact time
在 DeepSWE 基准上 Laguna S 2.1 得分 40.4，而 DeepSeek V4 Pro Max 仅约 9 分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
Valid until: 10/23/2026
Sources
Related Claims
UnverifiedDeepSeek V4 Pro scored 691 points in this evaluation, ranking first.74% similarVerifiedDeepSeek-V3 outperformed open-source models such as Qwen2.5 and Llama 3.1 in multiple benchmarks.72% similarUnverifiedDeepSeek V4 Pro's code engineering score of 62.7 is 7.3 points below Fable 5, its data science hard-level score of 67.2 trails Opus 4.8 by approximately 4.5 points, and its high-difficulty reasoning score of 60 ranks second globally.71% similarUnverifiedDeepSeek V4 ranks in the top three in the Agentic Capabilities evaluation.70% similarUnverifiedDeepSeek-V4-Pro has not yet surpassed the benchmark scores of top competitors as of now, and some benchmark scores are still estimated values.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/615375API
curl https://kongchang.com/api/v1/knowledge/claims/615375MCP
get_claim(id=615375)