List your company

Logical Reasoning on ProofWriter (Acc, TTFT, Delay (s))

81.3AccuracyStreamingThinker
57.3863.5969.876.01Oct 20, 2025

Evaluation results

MethodLinks
StreamingThinkerParadigm=Streaming, Reasoning Depth=D3, Model=Qwen3-4B2025.1081.320.5111.05
InterleavedParadigm=Interleaved, Reasoning Depth=D3, Model=Qwen3-4B2025.1080.120.5122.35
StreamingThinkerParadigm=Streaming, Reasoning Depth=D2, Model=Qwen3-4B2025.1076.120.516.5
InterleavedParadigm=Interleaved, Reasoning Depth=D2, Model=Qwen3-4B2025.107520.5118.07
BatchParadigm=Batch, Model=Qwen3-4B2025.1062232.1161.99
StreamingThinkerParadigm=Streaming, Reasoning Depth=D1, Model=Qwen3-4B2025.1058.820.510.71
InterleavedParadigm=Interleaved, Reasoning Depth=D1, Model=Qwen3-4B2025.1058.320.5111.96