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
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | GPT-5.4 | 1 | Gold |
| 2 | Claude Opus 4.6 | 0.9929 | Silver |
| 3 | DeepSeek V3.2 | 0.9893 | Bronze |
| 4 | Gemini 3.1 Pro Preview | 0.9839 | — |
| 5 | Grok 4.20 | 0.9236 | — |
| 6 | GLM-5 | 0.9165 | — |
| 7 | Qwen3 Coder Next | 0.7819 | — |
| 8 | Seed 2.0 Pro | 0.6973 | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | 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 |
Model results use the updated scores and medal thresholds. No valid score earns zero medal credit. Historical framework scores use the original evaluators and have not been updated alongside the model results.