Navers lab
← All tasks
InventoryOptimization Task 12 / 47

general_meio

General-topology multi-echelon inventory optimization (MEIO) with simulation-based expected cost objectives over stochastic demand, possibly including non-tree networks. Policy search targets base-stock–like parameters under sample-path evaluation—realistic MEIO engineering beyond trees.

Model leaderboard

# Participant Score
1 GPT-5.4 100.0
2 Claude Opus 4.6 97.7
3 DeepSeek V3.2 96.5
4 Gemini 3.1 Pro Preview 94.7
5 Grok 4.20 74.8
6 GLM-5 72.4
7 Qwen3 Coder Next 27.9
8 SEED 2.0 Pro 0.0

Framework leaderboard

# Participant Score
1 Claude Opus 4.6 + OpenEvolve 100.0
2 Claude Opus 4.6 + ShinkaiEvolve 91.7
3 GPT-OSS + OpenEvolve 86.3
4 GPT-OSS + ShinkaiEvolve 61.7
5 GPT-OSS + ABMCTS 60.5
6 Claude Opus 4.6 + ABMCTS 0.0

Score is the normalized score for this task (0–100, higher is better).