Expired50% confidenceBenchmarkExact time
The DeepSeek series' scores on SWE-bench are now on par with GPT-4o and Claude Sonnet.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/13/2026
First Seen
Valid until: 10/11/2026(expired)
Sources
Claude Code国内使用指南：模型选型与省钱配置全攻略
bilibili小伍不是码牛7/7/2026
Related Claims
UnverifiedThe DeepSeek series scores comparably to GPT-4o and Claude Sonnet on some programming tasks in public benchmarks such as HumanEval and SWE-bench.83% similarVerifiedDeepSeek V4's performance in code generation, mathematical reasoning, and other areas is on par with or surpasses top-tier models such as GPT-4o and Claude 3.5 Sonnet.80% similarVerifiedDeepSeek-V3 and DeepSeek-R1 have reached performance levels comparable to GPT-4o on multiple benchmarks.77% similarPartially VerifiedDeepSeek V4 Pro's SweetBench Pro score surpasses GPT 5.4 and is only slightly below GPT 5.5 and Claude Opus 4.776% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501864API
curl https://kongchang.com/api/v1/knowledge/claims/501864MCP
get_claim(id=501864)