MM-OptBench - Network Optimization: leaderboard

MM-OptBench (2026) asks multimodal models to turn a text specification plus visual artifacts such as tables, graphs, maps and schedules into an optimization formulation and solver code, which is run and checked against the verified optimum. This board is pass@1 in percent, the mean of five runs, on network optimization problems such as flows, paths and network design; higher is better.

Metric: pass@1 (%) on the network optimization (150 instances: flows, paths, network design) family, mean of five runs, solver-grounded: the model reads a text specification plus visual artifacts (tables, graphs, maps, schedules) and must return an optimization formulation and executable solver code whose returned objective matches the verified optimum, prompting only with no fine-tuning, retrieval or agentic repair; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)68.5#99
2GPT-5.439.6#135
3Qwen 3 VL Plus24.7#512
4GLM-4.5V16.4#754
5Qwen-VL-Max (MM-OptBench checkpoint unspecified)12.8
6Claude Sonnet 4.68.5#173

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=mm-optbench-network-optimization · How It Works · Data refreshed daily, snapshot 2026-11-21.