Standard Next-Token Prediction (NTP) baseline downstream evaluation performance after 60B mid-training tokens across 15 tasks covering Reasoning, Factual Recall, and Knowledge & Commonsense.

Standard Next-Token Prediction (NTP) baseline downstream evaluation performance after 60B mid-training tokens across 15 tasks covering Reasoning, Factual Recall, and Knowledge & Commonsense. · CiteArk

Measurement results

0/15 assessed

0 supported0 disputed or conflicting15 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Reported	Latest observation	Evidence judgment
40.4 percentage_points	—	Not assessed
29.8 percentage_points	—	Not assessed
23.1 percentage_points	—	Not assessed
29.9 percentage_points	—	Not assessed
29.8 percentage_points	—	Not assessed
3.8 percentage_points	—	Not assessed
56.7 percentage_points	—	Not assessed
25.5 percentage_points	—	Not assessed
8.7 percentage_points	—	Not assessed
43.6 percentage_points	—	Not assessed
15.5 percentage_points	—	Not assessed
51.1 percentage_points	—	Not assessed

Standard Next-Token Prediction (NTP) baseline downstream evaluation performance after 60B mid-training tokens across 15 tasks covering Reasoning, Factual Recall, and Knowledge & Commonsense.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results