OptiVerse - Stochastic Optimization: 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 stochastic optimization problems; higher is better.

Metric: Accuracy (%) on the 120 stochastic optimization 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

#ModelSettingScoreOverall rank
1Gemini 3 Pro56.67#146
2Gemini 3 Flash54.17#180
3Gemini 2.5 Pro50#280
4GPT-5.2Thinking50#190
5Qwen3-235B-Thinking (OptiVerse checkpoint unspecified)49.17
6Gemini 2.5 Flash48.33#466
7O4 Mini48.33#372
8Claude Sonnet 4.5Thinking46.67#267
9Qwen3-30B-Thinking (OptiVerse checkpoint unspecified)46.67
10O345.83#242
11Qwen 3 235B Instruct (OptiVerse checkpoint unspecified)45.83
12DeepSeek V3.2Thinking45#425
13Qwen 3 8BThinking41.67#1890
14Kimi K238.33#448
15Qwen 3 30B Instruct (OptiVerse checkpoint unspecified)31.67

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=optiverse-stochastic-optimization · How It Works · Data refreshed daily, snapshot 2026-11-22.