Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

PCB-Bench - Common Basic Fill in Blank — leaderboard

Metric: Accuracy (%). Source: digailab.github.io. 9 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro84
2Gemini 2.5 Flash Lite78.66
3GPT-575.67
4GPT-5 Nano73.33
5Llama 4 Maverick70.66
6Qwen 3 VL 235B A22B (Thinking)68
7Qwen 3 VL 8B Instruct58.66
8InternVL3-78B54.66

Interactive version: theaggregate.ai/benchmark?slug=pcb-bench-common-basic-fill-in-blank · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.