Expired50% confidenceBenchmarkExact time
Current top commercial models typically score no more than 10% on GAIA Level 3.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/12/2026
First Seen
Valid until: 10/10/2026(expired)
Sources
Related Claims
Unverified2023年人类在GAIA测试中的平均成功率约为90%，而当时最强的GPT-4在Level 1上仅勉强达到15%68% similarUnverifiedGAIA题目对人类来说相对简单，人类平均正确率约92%，但对顶级AI模型极具挑战性64% similarUnverifiedOn the ARC-AGI-3 benchmark, GPT-5.6 Sol scored 8%, while most other models scored below 2%; Anthropic did not run Fable due to prohibitively high costs.63% similarUnverified据行业估计，第三方意图数据的真阳性率通常仅在15%-30%之间62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/491954API
curl https://kongchang.com/api/v1/knowledge/claims/491954MCP
get_claim(id=491954)