Unverified50% confidenceBenchmarkExact time
Meta's "8161" model surpasses Opus and GPT-5.6 with a score of 77.0 in the evaluation data published by the model itself.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
Open-Source Models Outperform Closed-Source Flagships? GPT-5.6 Faces Open-Source Challenge
bilibili开源项目雷达站10/23/2026
Related Entities
Related Claims
UnverifiedMeta's newly released 816B-parameter model activates only about 5% of its parameters per token, with the actual parameter count involved in computation on the order of 40B.70% similarUnverifiedAt the mention level, the model achieved an overall precision of 74.1% and a recall of 70.5%.66% similarUnverifiedThe OCR model achieves an F1 score of 87% on a real invoice dataset.66% similarUnverifiedIn orchestration mode the local model scored 78/78 and 77/78; in single large-requirement mode it only got 76, 74, 71 (out of 78)64% similarVerifiedGLM 5.2 (submitted by the author themselves) scored 78.0 on this benchmark.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088508API
curl https://kongchang.com/api/v1/knowledge/claims/1088508MCP
get_claim(id=1088508)