Expired85% confidenceFactTime unknown
Gemini 3.5 Flash scored 40.2% on Humanities Last Exam, falling behind Opus's 46.9% and Pro's 44.4%.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
谷歌AntiGravity 2.0深度评测：桌面应用、Go重写CLI与Gemini 3.5 Flash实测
bilibili薛定猫AI
Related Entities
Related Claims
UnverifiedGemini 2.5 Pro scored 18.8% on the Humanities Last Exam benchmark, far exceeding O3 Mini's 14% and other models' scores below 10%.83% similarUnverifiedGemini 3.5 Flash scored 83.6% on the Agent task benchmark.82% similarUnverifiedGemini 3.5 Flash's coding capability benchmark score is 76.2%.79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16539API
curl https://kongchang.com/api/v1/knowledge/claims/16539MCP
get_claim(id=16539)