OR-Space - Explain: leaderboard
The Explain task of OR-Space (2026), a workspace benchmark for industrial optimization agents: from the workspace and solver outputs such as logs, duals and slacks, the agent writes short factual reports on bottlenecks and sensitivities. Scored 0-100 by a rubric with a hallucination penalty; higher is better.
Metric: Explain rubric score (0-100): exact coverage, reasoning, grounding and answer quality of short solver-grounded reports minus a hallucination penalty, checklist items scored programmatically or by a judge model, 100 industrial optimization instances in a filesystem workspace (docs, data and an empty or heuristic src directory), Gurobi 12.0.1 track, API temperature at most 0.1; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.4 | 86.52 | #135 | |
| 2 | GPT-5 Mini | 82.94 | #364 | |
| 3 | Claude Opus 4.6 | 80.2 | #113 | |
| 4 | Claude Sonnet 4.5 | Thinking | 79.63 | #261 |
| 5 | Qwen 3.5 27B | 77.88 | #375 | |
| 6 | DeepSeek V4 Flash | 77.77 | #267 | |
| 7 | GPT-5.1 | 76.16 | #240 | |
| 8 | Qwen 3 Max | 74.66 | #415 | |
| 9 | Gemini 3.1 Pro (Preview) | 73 | #99 | |
| 10 | DeepSeek V4 Pro | 68.87 | #196 | |
| 11 | Qwen 3 32B | Non-reasoning | 61.32 | #972 |
| 12 | Qwen 3 14B | Non-reasoning | 61.03 | #1269 |
| 13 | GPT-4o | 59.36 | #751 | |
| 14 | Qwen 3 8B | Non-reasoning | 55.19 | #1873 |
| 15 | Gemini 3 Flash | 53.24 | #175 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=or-space-explain · How It Works · Data refreshed daily, snapshot 2026-11-21.