Unverified50% confidenceFactExact time
EmbeddingGemma 2's context window was expanded from v1's 2048 tokens to 8192, MTEB Code improved from 68.76 to 78.68, and it already supports Ollama, llama.cpp, sentence-transformers, MLX, vLLM, and browser-side transformers.js; there is currently no independent retrieval benchmark test for v2, and the SciFact score of 0.7861 belongs to v1.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedZed v1.17.1-pre fixes an issue where project-level language server settings were ignored by extensions (#63082), affecting extensions built on the v0.1.0 and earlier extension API versions.60% similarUnverifiedv2.1.289 reverts a fix for the frequent logout issue caused by claude auth status under VSCode (which originated from a change in 2.1.288).57% similarUnverifiedThe H01–H12 suite contains nine expected field updates and 291 protected field slots.57% similarUnverifiedVersion 1.0.126 contains two major changes: upgrading the compilation target to ES2022 and refactoring the sandbox API.56% similarUnverifiedOllama v0.40.4-rc0 的唯一变更是 MLX 和 MLX-C 的版本升级（PR #18956），无新功能、API 变更或破坏性改动。56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018776API
curl https://kongchang.com/api/v1/knowledge/claims/1018776MCP
get_claim(id=1018776)