Unverified50% confidenceBenchmarkExact time
On calibration, Jev's ECE in independent tests varies between 0.02 and 0.35 depending on the task; Laya's ECE is 0.466 before temperature fitting (overconfident) and drops to 0.081 after fitting; Drex has not published calibration data.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedLayla's official claim of a calibration error of 0.081 outperforming Jev is the result after re-fitting the temperature; the native calibration error is actually worse than Jev's, and the multilingual version ships with an empty temperature table, causing probability collapse.70% similarUnverifiedAfter fine-tuning, Laya reaches 0.766 on the same benchmark, versus the third-party-published Jev figure of 0.727; Drex offers fine-tuning as a vendor service.64% similarUnverifiedOn 300 practice exam papers labeled by Qwen3-32B, fine-tuned v3 of Laya raised the judgment macro-F1 across 11 questions from 0.33 to 0.57 versus the zero-shot version, cut calibration error from 0.15 to 0.07, and reduced danger-level MAE from 2.78 to 1.56.62% similarUnverifiedOn the 1,302 expert-annotated trajectories of AgentRewardBench, JEV-27B-VL reports an AUROC of 0.91, with precision 78.4 and recall 70.2 at a threshold of 0.5.61% similarUnverifiedThe method achieves an MSE of 0.007 ± 0.005 on the BraTS 2026 validation set.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065253API
curl https://kongchang.com/api/v1/knowledge/claims/1065253MCP
get_claim(id=1065253)