Unverified50% confidenceCautionExact time
There is currently no independent third-party evaluation; 'smarter than comparable models, faster than most dense models' is the team's self-assessment.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
74B Model Squeezed into 24GB VRAM: Running Locally for Free on a Single 4090
bilibilijeffzhengye10/15/2026
Related Entities
Related Claims
Unverified综合多个独立来源的评测结果比单一自报基准分数更能反映模型的实际水平73% similarUnverifiedThere are many evaluations of embedding models and reranking models in the community, but end-to-end studies that treat parsing quality as an independent variable are very few.70% similarVerifiedA model with slightly lower accuracy but well-calibrated confidence is often more suitable for production deployment than a model with higher accuracy that is blindly overconfident.69% similarUnverifiedA high score on any single benchmark test (such as 99.9%) only shows that the model performs excellently within the distribution of that test's questions, and cannot be directly equated with general intelligence.69% similarUnverifiedThe same model may rank very differently across different evaluation platforms.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037464API
curl https://kongchang.com/api/v1/knowledge/claims/1037464MCP
get_claim(id=1037464)