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

测量结果

已评估 0/66 项

获得支持 0有争议或冲突 0尚未评估 66

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
model: Qwen3-1.7B · method: AutoRegressive · dataset: AIME25	2,454.4 output token/s	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: AIME25	1 × AutoRegressive	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: CodeElo	2,044 output token/s	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: CodeElo	1 × AutoRegressive	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB[16k-18k]	1,195.1 output token/s	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB[16k-18k]	1 × AutoRegressive	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[30k-40k]	544.7 output token/s	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[30k-40k]	1 × AutoRegressive	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[80k-100k]	210.5 output token/s	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: LB-v2[80k-100k]	1 × AutoRegressive	—	尚未评估
model: Qwen3-1.7B · method: AutoRegressive · dataset: all five workloads	1 × AutoRegressive	—	尚未评估
model: Qwen3-1.7B · method: MagicDec · dataset: AIME25	4,726.4 output token/s	—	尚未评估

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果