Unverified50% confidenceBenchmarkExact time
EmsyAI uses a 2.3 million parameter LoRA adapter for instruction fine-tuning on the CodeAlpaca dataset, achieving a score of 0.0% on the HumanEval code benchmark.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedHumanEval was developed in-house by OpenAI and is specifically designed to test the functional correctness rate of code generation.69% similarVerifiedHumanEval是由OpenAI于2021年发布的代码生成基准测试，包含164个手写的Python编程问题67% similarUnverifiedHumanEval基准测试由OpenAI于2021年随Codex模型论文一同发布，包含164道编程题，Pass@1指一次生成即通过全部测试用例的比例66% similarUnverifiedModern code generation models have already achieved a one-pass success rate of over 90% on authoritative code benchmarks such as HumanEval.63% similarUnverifiedCode large language models are evaluated using executable benchmarks such as HumanEval and MBPP, meaning the generated code is directly executed and the output is checked for correctness.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/912652API
curl https://kongchang.com/api/v1/knowledge/claims/912652MCP
get_claim(id=912652)