Unverified50% confidenceFactExact time
GPQA Diamond is a benchmark testing graduate-level scientific reasoning ability, with ordinary human performance at approximately 35% and top closed-source models in the 60–75% range.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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%75% similarUnverifiedGPQA is a graduate-level question-answering benchmark introduced in 2023; even with the aid of a search engine, non-experts achieve a correct answer rate of only about 30%.70% similarUnverifiedThe evaluation covered five benchmarks: MMLU-Pro, GPQA Diamond, GSM8K, German MGSM, and IFEval.66% similarUnverifiedIn the GPQA-Diamond xhigh test, the base model Qwen3.8-27B achieves 88.4% accuracy consuming 6,642 median tokens, while Swift maintains 88.3% accuracy with tokens reduced to 2,77163% 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%63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949604API
curl https://kongchang.com/api/v1/knowledge/claims/949604MCP
get_claim(id=949604)