Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Asynchronous planning on AsyncHow
Loading...
98.44
Makespan Accuracy
DeepSeek-V4-Flash
54.24
65.715
77.19
88.665
May 31, 2026
Makespan Accuracy
Updated 1d ago
Evaluation Results
Method
Method
Links
Makespan Accuracy
DeepSeek-V4-Flash
Approach=CP-SAT Formal...
2026.05
98.44
CP-SAT Formalizer
Solver=CP-SAT, Average...
2026.05
97.5
GPT-5-mini
Approach=CP-SAT Formal...
2026.05
97.5
Qwen3.6 35B A3B
Approach=CP-SAT Formal...
2026.05
97.19
Gemini-3-flash
Approach=CP-SAT Formal...
2026.05
96.88
GPT-5-mini
Approach=Planner
2026.05
96.56
DeepSeek-V4-Flash
Approach=Planner
2026.05
96.56
Gemini-3-flash
Approach=PDDL2.1 Forma...
2026.05
96.25
Qwen3.6 35B A3B
Approach=Planner
2026.05
95.63
Planner
Averaged=four LLMs
2026.05
94.4
Gemini-3-flash
Approach=Planner
2026.05
88.75
GPT-5-mini
Approach=PDDL2.1 Forma...
2026.05
85
DeepSeek-V4-Flash
Approach=PDDL2.1 Forma...
2026.05
80
PDDL2.1 Formalizer
Solver=OPTIC, Averaged...
2026.05
79.3
Qwen3.6 35B A3B
Approach=PDDL2.1 Forma...
2026.05
55.94
Feedback
Search any
task
Search any
task