On Qwen3-1.7B, ASPIRE reported 2.06×, 2.12×, 3.78×, 4.17×, and 4.58× AutoRegressive throughput across the five workloads and the best overall mean at 3.34×. It was not the best individual method on every workload: Vegas was marginally higher on AIME25, ASPIRE-Fixed was higher on CodeElo, and ASPIRE-FSM was marginally higher on LB-v2[30k-40k].

On Qwen3-1.7B, ASPIRE reported 2.06×, 2.12×, 3.78×, 4.17×, and 4.58× AutoRegressive throughput across the five workloads and the best overall mean at 3.34×. It was not the best individual method on every workload: Vegas was marginally higher on AIME25, ASPIRE-Fixed was higher on CodeElo, and ASPIRE-FSM was marginally higher on LB-v2[30k-40k]. · CiteArk

Measurement results

0/66 assessed

0 supported0 disputed or conflicting66 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
model: Qwen3-1.7B · method: AutoRegressive · dataset: AIME25	2,454.4 output token/s	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: AIME25	1 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: CodeElo	2,044 output token/s	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: CodeElo	1 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB[16k-18k]	1,195.1 output token/s	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB[16k-18k]	1 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[30k-40k]	544.7 output token/s	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[30k-40k]	1 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[80k-100k]	210.5 output token/s	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[80k-100k]	1 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · method: AutoRegressive · dataset: all five workloads	1 × AutoRegressive	—	Not assessed
model: Qwen3-1.7B · method: MagicDec · dataset: AIME25	4,726.4 output token/s	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results