Categoryexternal
MeasureMean reference-anchored log score, expressed as a percentage
Tasks4 autonomous research tasks
DifficultyAI research under fixed compute and time budgets
Tests autonomous AI research on compression, language-model training, judge-harness engineering, and post-training under fixed compute and time budgets.
No model in the catalog has a published Vals RSI Index score.The benchmark is defined by Vals RSI Index leaderboard and methodology, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
About Vals RSI Index
What the benchmark measures and how its value is published, from the source’s own record.
What is Vals RSI Index?
Vals RSI Index (Vals RSI Index v1.1) is an external benchmark published by Vals RSI Index leaderboard and methodology. Tests autonomous AI research on compression, language-model training, judge-harness engineering, and post-training under fixed compute and time budgets. Its evaluation set is described by the source as 4 autonomous research tasks. The source rates its difficulty as AI research under fixed compute and time budgets.
How is Vals RSI Index scored?
Each model's result is published by Vals RSI Index leaderboard and methodology as mean reference-anchored log score, expressed as a percentage. ModelScale prints that value to 2 decimal places, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale