Unverified50% confidenceBenchmarkExact time
GPT-4在2023年初于MMLU上取得86.4%的成绩
1
Sources
50%
Confidence
Long-term
Relevance
8/20/2026
First Seen
Sources
Related Claims
UnverifiedMMLU scores jumped from approximately 70% for GPT-3.5 to 86% for GPT-4, and then to above 90% for subsequent models.80% similarUnverifiedGPT-4 发布时在 MATH 数据集上的正确率为 42.5%75% similarUnverifiedOn mainstream benchmarks such as MMLU, HumanEval, and GSM8K, open-source models have reached 85–95% of the level of early versions of GPT-4.75% similarUnverifiedGPT-4 was launched in 2023 with an estimated parameter scale exceeding one trillion.75% similarUnverifiedIn 2023, GPT-4 achieved a passing score of 60 or above on all three stages of the USMLE, with some studies reporting scores approaching the average medical student level.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/780098API
curl https://kongchang.com/api/v1/knowledge/claims/780098MCP
get_claim(id=780098)