InventoryOptimization
Task 13 / 47
joint_replenishment
Multi-SKU joint replenishment with shared setup or truck costs: choose lot sizes and timings to trade holding versus stockout under stochastic or deterministic demand. Mixed structure reflects retail distribution "order pooling" combinatorics scored by total cost or service level.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 0.8822 | Gold |
| 1 | DeepSeek V3.2 | 0.8822 | Gold |
| 1 | Gemini 3.1 Pro Preview | 0.8822 | Gold |
| 1 | GLM-5 | 0.8822 | Gold |
| 1 | Grok 4.20 | 0.8822 | Gold |
| 1 | Seed 2.0 Pro | 0.8822 | Gold |
| 7 | Qwen3 Coder Next | 0.8821 | — |
| — | GPT-5.4 | No valid score | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | GPT-OSS + OpenEvolve | 100.0 |
| 2 | Claude Opus 4.6 + OpenEvolve | 0.2 |
| 3 | Claude Opus 4.6 + ShinkaiEvolve | 0.2 |
| 4 | GPT-OSS + ShinkaiEvolve | 0.2 |
| 5 | Claude Opus 4.6 + ABMCTS | 0.2 |
| 6 | GPT-OSS + 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.