OmniSch - Pin Detection: leaderboard

Schematic-to-netlist conversion on OmniSch (2026): from a PCB schematic image exported by an industrial EDA tool, the model generates the netlist graph of symbols, pins and nets in one zero-shot prompt, compared with reference graphs extracted automatically from the schematic source files. F1 of pin detection under name and structure matching, times 100; higher is better.

Metric: Pin detection F1 (x100): ground-truth pins matched by the pin matching score of Eq. 2 (net, pin and pad names and coarse structure) on the industrial-EDA (Real) schematics of the OmniSch held-out test split, the model converting each PCB schematic image into a spatially weighted netlist graph with one zero-shot prompt, predicted and reference nodes aligned by maximum-weight bipartite matching; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1OmniSch Gemini 2.5 Flash (checkpoint unspecified)70.62
2Gemini 3.1 Pro (Preview)69.28#99
3Claude Sonnet 4.655.13#173
4Qwen 3.5 122B A10B51.64#346
5GPT-5.251.55#185
6Ministral 3 14B37.94#1870
7GPT-5 Mini36.58#364
8Llama 4 Maverick24.05#1110
9Qwen 3 VL 8B Instruct1.95#1029

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

Interactive version: theaggregate.ai/benchmark?slug=omnisch-pin-detection · How It Works · Data refreshed daily, snapshot 2026-11-21.