OptiVerse - Mathematical Programming: leaderboard
OptiVerse (2026) is a benchmark of textbook-sourced optimization problems that models solve by writing and running solver code, a problem counting as solved only when every required value matches the ground truth within 0.1%. This board is accuracy in percent on the mathematical programming problems; higher is better.
Metric: Accuracy (%) on the 367 mathematical programming problems of OptiVerse; the model writes and runs solver code (gurobi, pyomo, cvxpy, ortools and others) and a problem counts as solved only when every required variable and the objective match the ground truth within 0.1% relative error, extracted and checked by a DeepSeek-V3.2-Chat judge; 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 | Gemini 3 Pro | 58.04 | #145 | |
| 2 | GPT-5.2 | Thinking | 55.86 | #185 |
| 3 | Gemini 3 Flash | 54.77 | #175 | |
| 4 | Gemini 2.5 Pro | 53.68 | #276 | |
| 5 | DeepSeek V3.2 | Thinking | 53.68 | #419 |
| 6 | Qwen3-235B-Thinking (OptiVerse checkpoint unspecified) | 53.68 | ||
| 7 | Claude Sonnet 4.5 | Thinking | 53.41 | #261 |
| 8 | O3 | 52.04 | #237 | |
| 9 | O4 Mini | 50.95 | #368 | |
| 10 | Qwen3-30B-Thinking (OptiVerse checkpoint unspecified) | 49.59 | ||
| 11 | Gemini 2.5 Flash | 46.05 | #463 | |
| 12 | Qwen 3 235B Instruct (OptiVerse checkpoint unspecified) | 44.41 | ||
| 13 | Qwen 3 8B | Thinking | 40.33 | #1873 |
| 14 | Kimi K2 | 40.05 | #443 | |
| 15 | Qwen 3 30B Instruct (OptiVerse checkpoint unspecified) | 38.96 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=optiverse-mathematical-programming · How It Works · Data refreshed daily, snapshot 2026-11-21.