List your company

Planning on PlanningBench 1.0 (test)

63.17All-pass RateGPT-5.4-xhigh
-2.526814.529131.58548.6409May 20, 2026

Evaluation results

MethodLinks
GPT-5.4-xhighType=Closed-source2026.0563.1792.35
GPT-5.4-highType=Closed-source2026.0558.5684.6
GPT-5.4-mediumType=Closed-source2026.0558.0990.03
Gemini-3-1-proType=Closed-source2026.0553.2588.36
Seed-2.0-pro-highType=Open-source2026.0544.3384.02
DeepSeek-V3.2-thinkingType=Open-source2026.0537.1380.21
Hy3-PreviewType=Open-source2026.0536.1778.14
Qwen3.5-plus-thinkingType=Open-source2026.0534.0377.1
DeepSeek-R1Type=Open-source2026.0533.0774.04
Gemini-2.5-proType=Closed-source2026.0531.776.41
Seed-2.0-pro-mediumType=Open-source2026.0530.6377.09
DeepSeek-V3.2-expType=Open-source2026.0529.2776.69
Hy2.1Type=Open-source2026.0524.6171.18
Seed-1.8Type=Open-source2026.0522.471.69
Qwen3-30b-moeType=Open-source2026.0512.1557.4
Qwen3-32bType=Open-source2026.050.2730.11
Qwen3-14bType=Open-source2026.05025.69
Qwen3-8bType=Open-source2026.05022.79