Unverified50% confidenceBenchmarkExact time
The accuracy after same-category substitution differs from the original accuracy by no more than 5.2 percentage points.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
UnverifiedWhen 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%.78% similarUnverifiedLID accuracy at switching points is typically 10–20 percentage points lower than LID accuracy at non-switching points.76% similarUnverified4-bit quantization compared to FP16 typically results in a 0.5–2% drop in benchmark accuracy.74% similarUnverifiedAfter excluding the three collapsed scorers, the compliance rates on the four remaining corpora still differ by 1.7 to 2.8 times, and the non-refusal rates differ by 10 to 22 percentage points.74% similarUnverifiedLooking only at the two check packs, the fully accurate rate rose from 94.4% to 96.0%.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1105812API
curl https://kongchang.com/api/v1/knowledge/claims/1105812MCP
get_claim(id=1105812)