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 - Task 3 SBERT — leaderboard

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

Top models

#ModelScore
1Qwen 3 VL 235B A22B (Thinking)61.68
2GPT-561.34
3Qwen 3 VL 8B Instruct57.6
4Gemini 2.5 Pro56.26
5GPT-5 Nano53.58
6Llama 4 Maverick51.01
7Gemini 2.5 Flash Lite50.83
8InternVL3-78B48.5

Interactive version: theaggregate.ai/benchmark?slug=pcb-bench-task-3-sbert · 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.