Unverified50% confidenceBenchmarkExact time
Under a 96-token context, ILRN's held-out test set top-1 accuracy was 27.17%, and Transformer's was 25.83%.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCaveman's fixed benchmark test results from 54 runs show a 33.2% reduction in input tokens, with all 18/18 correctness checks passing.69% similarUnverifiedState-of-the-art supervised models on the LIAR benchmark still hover around 28%–32% six-class accuracy.69% similarUnverified在Transformer架构中，每个参数在BF16精度下占2字节，INT8精度下占1字节，INT4精度下占0.5字节67% similarUnverifiedThe locally run Gemma 26B achieved an accuracy of only 49.2% across 453 scored predictions, while its paired always-predict-up baseline had an accuracy of 53.4%.66% similarUnverifiedIn Microsoft's internal evaluation covering 36 benchmarks and nearly 150,000 questions, Decision-1 ranked first with an average accuracy of 83.5%, surpassing Jev 1.13.0 (82.3%), Quyet-1.0-Large (81.9%), and GPT-6 Luna Decisions (79.4%).65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013015API
curl https://kongchang.com/api/v1/knowledge/claims/1013015MCP
get_claim(id=1013015)