Unverified50% confidenceBenchmarkExact time
In the 30-day holdout evaluation, TabPFN v2 had the lowest error with an MAE of 10.3 and RMSE of 14.6, and the 95% confidence interval for its MAE advantage over B2 was −17.0 to −6.9.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the 30-day holdout evaluation, untuned HistGBR (B5) approached TabPFN with an MAE of 10.8 on the validation month, and TabPFN's ranking advantage over B2 was not significant at that sample size.72% similarUnverifiedIn the 12-week short-term prediction, Ridge regression performed best, with an RMSE of 5.186 and an R² of 0.474.65% similarUnverifiedIn the LongMemEval benchmark, BM25 accuracy improved from 78.8% to 85.2% with 5 chunks.62% similarUnverifiedIn a model comparison test, qwen2.5:3b correctly understood pace, produced 0 hallucinated place names, had a length error of 0.3%, peak memory of 259 MB, and took 106 seconds.62% similarUnverifiedOn pure reasoning tasks, Qwen3 27B scores only 30.8 on HLE, notably behind Opus's score of 40.0.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002627API
curl https://kongchang.com/api/v1/knowledge/claims/1002627MCP
get_claim(id=1002627)