Unverified50% confidenceBenchmarkExact time
Grok still has a certain gap compared to GPT-4o and Claude 3.5 Sonnet on programming-specific benchmark tests such as HumanEval and MBPP.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/3/2026
First Seen
Valid until: 12/2/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-5、Grok 4等模型在基准测试（如HumanEval、SWE-bench）上表现优异，但这些测试通常是单次代码生成，与需要多轮工具调用的真实工程任务存在显著差距76% similarUnverifiedThe DeepSeek series scores comparably to GPT-4o and Claude Sonnet on some programming tasks in public benchmarks such as HumanEval and SWE-bench.76% similarUnverifiedOn the SWE-bench software engineering task benchmark, the task completion rates of Claude 3.5 Sonnet and GPT-4o far exceed those of open-source models.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/850118API
curl https://kongchang.com/api/v1/knowledge/claims/850118MCP
get_claim(id=850118)