Skip to content

DeepPlanning

A long-horizon planning benchmark that tests whether agents can optimize under explicit time, budget, and feasibility constraints.

7 models

Higher is better.

  1. 1Qwen3.7 PlusAlibaba62.3
  2. 2Qwen3.6 PlusAlibaba41.5
  3. 3Qwen3.5 397BAlibaba37.6
  4. 4Claude Opus 4.5Anthropic26.4
  5. 5Qwen3.6-35B-A3BAlibaba25.9
  6. 6GLM-5Z.AI14.6
  7. 7Kimi K2.5Moonshot AI14.4
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Long-horizon planning benchmark
Tasks
Travel planning and constrained shopping
Authors
DeepPlanning authors (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.