Unverified50% confidenceBenchmarkExact time
In a 2024 evaluation, GenCast's 15-day ensemble forecast skill surpassed ECMWF's operational ensemble forecasting system ENS on more than 97% of metrics.
1
Sources
50%
Confidence
Long-term
Relevance
8/10/2026
First Seen
Sources
DeepMind开源WeatherNext：AI气象预测新标杆
Related Claims
UnverifiedGenCast的精度超越欧洲中期天气预报中心（ECMWF）的传统数值模型65% similarUnverified参数量在1亿以下的轻量模型经领域数据微调后可达95%以上意图分类准确率，单次推理延迟控制在5-20ms以内63% similarUnverifiedIn early 2023, mainstream models' SWE-bench scores were generally below 5%; by mid-2025, top models had surpassed 70%.63% similarVerifiedIn 2024, top models achieved a pass rate of approximately 50–70% on SWEbench-Verified.62% similarUnverifiedThe solve rate of top models on SWE-bench jumped from under 5% in 2023 to over 30% in 2025.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/727052API
curl https://kongchang.com/api/v1/knowledge/claims/727052MCP
get_claim(id=727052)