List your company

Science Question Answering on GPQA-D (Acc, Tok)

68.5AccuracyPACT
57.26860.18463.166.016Jun 3, 2026

Evaluation results

MethodLinks
PACTBase Model=Qwen3-32B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0668.516,271
Multi-Agent DebateBase Model=Qwen3-32B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0666.477,888
CoABase Model=Qwen3-32B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0665.718,535
TextMASBase Model=Qwen3-32B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0665.721,428
PACTBase Model=Qwen3-14B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0662.515,935
Multi-Agent DebateBase Model=Qwen3-14B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0661.881,878
CoABase Model=Qwen3-14B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0661.618,789
TextMASBase Model=Qwen3-14B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.066116,366
PACTBase Model=Qwen3-8B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0660.419,960
CoABase Model=Qwen3-8B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0659.522,563
TextMASBase Model=Qwen3-8B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.065920,357
Multi-Agent DebateBase Model=Qwen3-8B, Pipeline Setting=four-agent sequential pipeline (Setting B)2026.0657.785,351