Unverified50% confidenceBenchmarkExact time
TTM 在 ETT-1 数据集上的 MSE 仅为 0.363，超越了 TimesFM、PatchTST 等大模型
1
Sources
50%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
Related Claims
UnverifiedThe original Codex achieved a pass@1 score of 28.8% on the HumanEval benchmark, whereas using GPT-3 directly yielded only 0%.54% similarUnverifiedIn a test of 15 large models developing the Bilibili homepage, ChatGPT 5.4 ranked first overall with a total score of 82.53% similarUnverifiedRTX 3060的INT4 Tensor Core理论峰值算力约为101 TOPS，而FP16仅约12.7 TFLOPS，差距达8倍以上53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/500135API
curl https://kongchang.com/api/v1/knowledge/claims/500135MCP
get_claim(id=500135)