Unverified50% confidenceBenchmarkExact time
The best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe study found that GPT-4's accuracy on the prime number identification task plummeted from 97.6% in March 2023 to 2.4% in June 2023.74% similarUnverified在GPT-4发布初期，主流模型在GPQA上的准确率约为35-40%，人类领域专家基准线约为65%，随机猜测为25%74% similarUnverifiedGPTQ（2022年）和AWQ（2023年）能将70B参数的LLM量化到INT4精度，困惑度损失不到1%70% similarUnverified4Bit量化下模型的基准测试得分通常能保持原始精度的90%-95%70% similarUnverifiedOn Artificial Analysis's Omniscience hallucination metric, GPT-5.6 Sol Max reached 89%, higher than Claude Fable's 55% and GLM 5.2's 28%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893229API
curl https://kongchang.com/api/v1/knowledge/claims/893229MCP
get_claim(id=893229)