Unverified50% confidenceBenchmarkExact time
According to Achint Srivastava's blog, Microsoft-Decision-1 had the highest accuracy in Microsoft's comparison of 36 benchmarks, with about 150,000 questions kept blind during training.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedAfter 15 training epochs on the demonstration dataset, the text classification model achieves an accuracy of 99%, with a total of 110,000 model parameters (16,000 for Attention, 33,000 for FFN, and the remainder for Embedding)69% similarUnverifiedWhen using the multi-agent verification process, MARCH's accuracy was suppressed to 4.4%, whereas when the same model was directly asked which solution was better, accuracy reached 43.7%.67% similarUnverifiedMicrosoft Discovery uses Decision-1 to score experiments in adaptive replanning loops, reporting that the model's scoring is 46 times more consistent and 3 times faster than LLM-based scoring.64% similarUnverifiedThe user pointed out that these models achieve high scores on benchmarks yet frequently fail at the simplest tasks.63% similarUnverifiedThe 29-million-parameter encoder trained by the researchers achieved a popularity-weighted cross-fold AUC of only 0.486 on 985 statements, indistinguishable from the corpus prior.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006147API
curl https://kongchang.com/api/v1/knowledge/claims/1006147MCP
get_claim(id=1006147)