Unverified50% confidenceBenchmarkExact time
Compared with the best-performing simple generator, the model leads on 5 of 6 items on the main test set, with advantages of 0.7 to 2.5 percentage points, and the test can prove the gap for 1 of those items.
1
Sources
50%
Confidence
Long-term
Relevance
11/9/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在MATH数据集的Level 5竞赛级难题上,前沿模型准确率仍低于60%74% similarUnverifiedIn the specific experimental case, the overlapping-anchor scheme (n=912) showed the model at 55.2% versus the majority class at 51.1%, a net advantage of +4.1pp, about 2.4 standard errors; the non-overlapping-anchor scheme (n=163) showed 59.5% versus 54.0%, a net advantage of +5.5pp, about 1.4 standard errors.74% similarUnverifiedThe gap between selection and generation exceeds 50 percentage points, revealing that reliability is far lower than benchmarks suggest when users need the model to directly write out kinship terms.72% similarUnverifiedOn the temporal split test set (878 comparisons from 655 trials), a gradient-boosted emulator trained on registry data eliminated about one-fifth of the error of a simple baseline.72% similarUnverifiedThe test sample size is relatively limited (5 models, 13 codebases), and the conclusions await validation at a larger scale.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1152041API
curl https://kongchang.com/api/v1/knowledge/claims/1152041MCP
get_claim(id=1152041)