Unverified50% confidenceFactExact time
EgoDex's held-out test set contains 3,243 episodes covering 111 types of tasks.
1
Sources
50%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGemma 4's E2B version performs comparably to Gemma 3's 27.1-billion-parameter model on multiple tasks in community benchmark tests.52% similarUnverified在 Terminal Bench 2.1 测试中,AutoPrompt Scale 使 OpenCode 在 89 个任务中的失败数从 29 降到 16,多解决 13 题,分数提升 14.61 个百分点51% similarUnverified在285次实测运行中,Gemini取得283次语义通过、2次语义部分通过、0次可复现语义失败51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/821173API
curl https://kongchang.com/api/v1/knowledge/claims/821173MCP
get_claim(id=821173)