Unverified85% confidenceFactExact time
GenCast的精度超越欧洲中期天气预报中心（ECMWF）的传统数值模型
1
Sources
85%
Confidence
Long-term
Relevance
5/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn a 2024 evaluation, GenCast's 15-day ensemble forecast skill surpassed ECMWF's operational ensemble forecasting system ENS on more than 97% of metrics.65% similarUnverifiedOn the CLINC150 benchmark, 80 fine-tuning samples can bring vector routing to an accuracy of 85.9%, while a full fine-tune can exceed 96%.55% similarVerifiedIn 2024, top models achieved a pass rate of approximately 50–70% on SWEbench-Verified.55% similarUnverifiedDomestic models such as GLM5.1 have achieved scores on standard programming benchmarks like HumanEval and MBPP that are close to or even surpass some international competitors.54% similarUnverified研究者通常使用期望校准误差（ECE）来量化模型的校准程度53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/10679API
curl https://kongchang.com/api/v1/knowledge/claims/10679MCP
get_claim(id=10679)