Expired60% confidenceReleaseExact time
Tencent released HY4 with vision capabilities, covering scenarios such as coding, front-end, finance and gaming; according to Tencent's own testing, it scores 75.2 on Apex Agents, higher than DeepSeek 4.1 Flash's range of 72 to 73.
2
Sources
60%
Confidence
Short-term (~14 days)
Relevance
11/4/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 11/18/2026(expired)
Sources
GPT-6.2 Astra Leaked: Low-End Config Beats Previous Top-Tier, SVG Generation Stuns
youtubeWorldofAI11/4/2026
Related Entities
Related Claims
UnverifiedDeepSeek's model V4 Flash 0731 achieved a score of 82.7% on Terminal-Bench 2.1.68% similarVerifiedArtificial Analysis evaluation shows DeepSeek V4.1 Flash scored 40 on the Intelligence Index, surpassing V4 Pro to become DeepSeek's new flagship, featuring native multimodal input, 8B activated parameters on input and 16B on output, released under the MIT license.68% similarUnverifiedIn the Intelligence Index V5 released by Artificial Analysis, Cloud Opus 5.5 ranks first with 58 points, and DeepSeek V4.1 Flash ties for first among open-weight models with 32 points.65% similarUnverifiedIn the black hole demo project, DeepSeek V4.1 Flash performed the best and received 90 points, while GLM5.3 Flash came in last.65% similarUnverifiedThere is no all-around winner among the three lightweight models: DeepSeek V4.1 Flash has the highest quality but is slow, Haiku 5.5 is fast and leads in writing but lags in programming visual output, and GPT-6 Luna performed poorly on tasks.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134806API
curl https://kongchang.com/api/v1/knowledge/claims/1134806MCP
get_claim(id=1134806)