The twelve reported checkpoints span routed-expert pools of 32–512 and native selections of 4–10 routed experts per token, with model roles and parameter counts reported in Table 1.

The twelve reported checkpoints span routed-expert pools of 32–512 and native selections of 4–10 routed experts per token, with model roles and parameter counts reported in Table 1. · CiteArk

Measurement results

0/60 assessed

0 supported0 disputed or conflicting60 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.
Metric and conditions	Reported	Latest observation	Evidence judgment
printedValue: 30.5B	30.5 billion parameters	—	Not assessed
printedValue: 3.3B	3.3 billion parameters	—	Not assessed
printedValue: 128	128 experts	—	Not assessed
printedValue: 8	8 experts	—	Not assessed
printedValue: 0	0 experts	—	Not assessed
printedValue: 80B	80 billion parameters	—	Not assessed
printedValue: 3B	3 billion parameters	—	Not assessed
printedValue: 512	512 experts	—	Not assessed
printedValue: 10	10 experts	—	Not assessed
printedValue: 1	1 experts	—	Not assessed
printedValue: 16.8B	16.8 billion parameters	—	Not assessed
printedValue: 2.75B	2.75 billion parameters	—	Not assessed

The twelve reported checkpoints span routed-expert pools of 32–512 and native selections of 4–10 routed experts per token, with model roles and parameter counts reported in Table 1.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results