List your company

Planning on PlanBench Blocksworld Mystery (test)

98.1Plain Text AccuracyGPT5
-3.92422.56349.0575.537Feb 3, 2026

Evaluation results

MethodLinks
GPT5Prompting=Plain Text, Model Category=LRM2026.0298.1—
o1Prompting=Plain Text, Model Category=LRM2026.0274.3—
o1preview*Prompting=Plain Text, Model Category=LRM2026.0252.8—
o1miniPrompting=Plain Text, Model Category=LRM2026.0219.1—
GPT4Prompting=Plain Text, Model Category=LLM2026.020—
GPT4oPrompting=Plain Text, Model Category=LLM2026.020—
GPT4Prompting=TMK, Model Category=LLM2026.02—3.8
GPT4oPrompting=TMK, Model Category=LLM2026.02—5.5
GPT5Prompting=TMK, Model Category=LRM2026.02—98.3
o1Prompting=TMK, Model Category=LRM2026.02—83.3
o1miniPrompting=TMK, Model Category=LRM2026.02—16.83