Unverified50% confidenceBenchmarkExact time
In a head-to-head comparison with four external PT-BR models, the lower bound of the Wilson confidence interval for the safety rate of Manacá-1B-Instruct-2 is 94.1%, higher than the upper bounds of all four baseline models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
VerifiedThe 95% Wilson confidence interval is more accurate than the normal approximation (Wald interval) when sample sizes are small or when proportions are close to 0 or 1.67% 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.63% similarVerifiedThe core insight of AWQ is that only approximately 1% of salient weights have a major impact on model output, and protecting them enables model quality to be maintained at extremely low bit widths62% similarUnverifiedThe 35B model achieved a pass rate of 90/90 under the constrained context, while the 4B model achieved 72/90.62% similarUnverifiedIn LSCBench, the six models' functional pass rate reached as high as 91.3%, but the highest simultaneous functional and security pass rate was only 25.1%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032797API
curl https://kongchang.com/api/v1/knowledge/claims/1032797MCP
get_claim(id=1032797)