Unverified50% confidenceBenchmarkExact time

GPT-OSS-120b has nearly a 50% chance of making JSON formatting errors when used outside of BAML.

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

9/22/2026

First Seen

Valid until: 12/21/2026

Sources

Jev: TypeSafe AI's First System 1 Model, Built Exclusively for Data Classification

Related Entities

GPT-OSS-120bmodel BAMLproduct

Related Claims

Unverified评测中使用GPT-OSS-120B配合Lemonade时，因Lemonade无法联网和读取本地文件，两次各约90分钟尝试后失败62% similar UnverifiedThe perplexity of the GPT series of models on Wikipedia text has decreased from approximately 29 for GPT-2 to an even lower level for GPT-4.59% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/940128

API

curl https://kongchang.com/api/v1/knowledge/claims/940128

MCP

get_claim(id=940128)