MM-OptBench - Easy: 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 the easy instances; higher is better.

Metric: pass@1 (%) on the 260 easy-level instances (10 per subcategory), 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
1GPT-5.467.6#135
2Gemini 3.1 Pro (Preview)64.5#99
3Claude Sonnet 4.638.8#173
4Qwen 3 VL Plus32.8#512
5GLM-4.5V29.3#754
6Qwen-VL-Max (MM-OptBench checkpoint unspecified)27.5

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-easy · How It Works · Data refreshed daily, snapshot 2026-11-21.