Unverified50% confidenceBenchmarkExact time
On the τ³-bench banking benchmark, EvoSkill v2 raises held-out pass rate by 5.4 percentage points over the stronger baseline.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedOn the SpreadsheetBench v2 benchmark, EvoSkill v2 raises held-out pass rate by 7.7 percentage points over the stronger baseline.78% similarVerifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.67% similarUnverifiedAfter re-evaluating with non-overlapping anchors, the net advantage instead grew from +4.1pp to +5.5pp, but significance dropped from 2.4 standard errors to 1.4 standard errors; the inflation factor is about 2.4x, exactly equal to sqrt(912/163).66% similarUnverifiedAt 16× compression, AdaMem's substring match improves by up to 3.2 percentage points (5.5%) over the uniform allocation baseline, with an average relative gain of 3.4%.65% similarUnverifiedExperiments show that SimOPD improves on the strongest baseline by an average of 2.6 percentage points under the same-architecture setting and by an average of 3.1 percentage points under the cross-architecture setting.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074283API
curl https://kongchang.com/api/v1/knowledge/claims/1074283MCP
get_claim(id=1074283)