Unverified50% confidenceBenchmarkExact time
Jev achieved 98.5% accuracy on English comments and 93.4% on the other seven languages, a gap of about 5 percentage points; the probabilities of the nine missed detections all ranged from 0.16 to 0.49, and it correctly identified the language in all 520 cases.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
Unverified即便单字符识别准确率达到99%，对于一个包含10个字符的字段，其整体正确率也仅约90%，这被称为"准确率衰减效应"73% similarUnverifiedAplomb 1 在 JevBench Hard 上得分 77.5%，在 MASSIVE 数据集 51 种语言上平均 75% 零样本意图识别准确率72% similarUnverifiedIn a scenario with 1,700 easy cases and 100 difficult multilingual cases, even if half of the difficult cases fail entirely, the aggregate pass rate may only drop from 97% to around 93%70% similarUnverifiedHuman test subjects achieve an average accuracy of over 85% on ARC problems, while mainstream large language models have long hovered below 20%.69% similarUnverifiedWhen Jev returns a confidence level above 0.95 (approximately 60% of messages), accuracy reaches 95.8%, indicating reliable confidence calibration quality69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015388API
curl https://kongchang.com/api/v1/knowledge/claims/1015388MCP
get_claim(id=1015388)