List your company

Sequence Understanding on Sequence Understanding Benchmark Average of 10 tasks

100Answer RateDeepSeek-V3
71.08878.59486.193.606Apr 9, 2026

Evaluation results

MethodLinks
DeepSeek-V3Protocol=Vanilla2026.0410045.7
DeepSeek-V3Protocol=CoT2026.0410044.5
DeepSeek-V3Protocol=ICL2026.0410045.2
DeepSeek-V3Protocol=SepSeq2026.0410050.9
Claude-3.7-SonnetProtocol=ICL2026.0410054.2
DeepSeek-R1Protocol=Vanilla2026.0499.961.1
DeepSeek-R1Protocol=CoT2026.0499.956.6
DeepSeek-R1Protocol=SepSeq2026.0499.970.5
Claude-3.7-SonnetProtocol=CoT2026.0499.957.6
Claude-3.7-SonnetProtocol=SepSeq2026.0499.979.1
DeepSeek-R1Protocol=ICL2026.0499.857.9
Claude-3.7-SonnetProtocol=Vanilla2026.0499.857.3
GPT-4.1Protocol=ICL2026.0499.860
GPT-4.1Protocol=Vanilla2026.0499.661
GPT-4.1Protocol=CoT2026.0499.660
GPT-4.1Protocol=SepSeq2026.0499.582.7
GPT-4oProtocol=Vanilla2026.049946.4
GPT-4oProtocol=ICL2026.0498.644.5
GPT-4oProtocol=SepSeq2026.0498.659.1
GPT-4oProtocol=CoT2026.0498.551.5
AverageProtocol=SepSeq2026.0492.868.9
AverageProtocol=Vanilla2026.0490.551.6
AverageProtocol=CoT2026.0490.348.9
Qwen3-30B-A3BProtocol=SepSeq2026.0490.280.7
AverageProtocol=ICL2026.0489.948.7
Qwen3-8BProtocol=SepSeq2026.0487.369.6
Gemini-2.5-ProProtocol=SepSeq2026.0484.679.1
Gemini-2.5-ProProtocol=Vanilla2026.0483.458.9
Gemini-2.5-ProProtocol=ICL2026.048256.9
Gemini-2.5-ProProtocol=CoT2026.0481.848
Qwen3-30B-A3BProtocol=ICL2026.048152.3
Qwen3-30B-A3BProtocol=CoT2026.0480.952.7
Qwen3-30B-A3BProtocol=Vanilla2026.0480.654.3
Qwen3-8BProtocol=CoT2026.0479.540.3
Qwen3-8BProtocol=Vanilla2026.0479.445.5
QwQ-32BProtocol=SepSeq2026.0475.657.8
Qwen3-8BProtocol=ICL2026.0475.238.5
QwQ-32BProtocol=Vanilla2026.0472.734.2
QwQ-32BProtocol=ICL2026.0472.728.5
QwQ-32BProtocol=CoT2026.0472.228.9