List your company

Question Answering on Choice QA MCTest

92.38AccuracyBatch (Full)
29.366445.725762.08578.4443May 30, 2026

Evaluation results

MethodLinks
Batch (Full)Backbone=Qwen-3-4B, Processing Mode=Offline2026.0592.38204.98100
Batch (Full)Backbone=Qwen2.5-3B-Instruct, Processing Mode=Offline2026.0588.33204.87100
Proactive-EntrBackbone=Qwen2.5-3B-Instruct, Processing Mode=Streaming2026.0585.83160.4678
Proactive-EntrBackbone=Qwen-3-4B, Processing Mode=Streaming2026.0583.33154.8175
Proactive-AttnBackbone=Qwen2.5-3B-Instruct, Processing Mode=Streaming2026.0583.15151.6274
Proactive-AttnBackbone=Qwen-3-4B, Processing Mode=Streaming2026.0582.15158.5675
Wait-9Backbone=Qwen-3-4B, Processing Mode=Streaming, Wait-k interval=92026.0547.9894
Wait-7Backbone=Qwen2.5-3B-Instruct, Processing Mode=Streaming, Wait-k interval=72026.0547.573
Wait-5Backbone=Qwen-3-4B, Processing Mode=Streaming, Wait-k interval=52026.0547.552
Wait-9Backbone=Qwen2.5-3B-Instruct, Processing Mode=Streaming, Wait-k interval=92026.0547.1494
Wait-5Backbone=Qwen2.5-3B-Instruct, Processing Mode=Streaming, Wait-k interval=52026.0545.7152
Wait-7Backbone=Qwen-3-4B, Processing Mode=Streaming, Wait-k interval=72026.0545.3673
Wait-3Backbone=Qwen2.5-3B-Instruct, Processing Mode=Streaming, Wait-k interval=32026.0543.131
Wait-3Backbone=Qwen-3-4B, Processing Mode=Streaming, Wait-k interval=32026.0531.7931