Unverified60% confidenceFactTime unknown
Experiments by the Long-Term team showed that using the same model with only adjustments to rule constraints and the memory system raised the score from 52.8% to 66.5%, jumping the ranking from Top 30 to Top 5.
2
Sources
60%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAcross five consecutive policy version iterations, the laboratory planning score improved from 21.80% to 46.01%73% similarUnverifiedAdding just one placeholder character to the system prompt alone can make a certain model jump from last place (58.2%) to first place (83.9%) on the same benchmark.72% similarUnverifiedIn the ablation study, when no data is used and only parametric memory is relied on, even the best model performs poorly; after providing early-quarter data, performance improves by about 25 percentage points; but there is still a 12-16 percentage point gap from using the latest data.70% similarUnverifiedOverall, model performance improves as parameter scale grows, and this trend holds for both cognitive and behavioral tasks, but the magnitude of improvement is not consistent across dimensions.70% similarUnverifiedMemory benchmark scores can fluctuate enormously depending on the evaluation protocol, and the same system may differ by more than ten percentage points under a different evaluation process.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38561API
curl https://kongchang.com/api/v1/knowledge/claims/38561MCP
get_claim(id=38561)