PCB-Bench - Placement Macro QA SBERT — leaderboard
Metric: SBERT similarity (%). Source: digailab.github.io. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 4 Maverick | 49.31 |
| 2 | DeepSeek V3.1 | 49.12 |
| 3 | Claude Opus 4.1 | 47.72 |
| 4 | GPT-4o | 47.56 |
| 5 | GPT-5 | 45.02 |
| 6 | MythoMax-L2-13B | 44.96 |
| 7 | Gemini 2.5 Pro | 41.72 |
| 8 | InternVL3-78B | 41.62 |
| 9 | Qwen 2.5 7B Instruct | 22.36 |
Interactive version: theaggregate.ai/benchmark?slug=pcb-bench-placement-macro-qa-sbert · How the rankings work · Data refreshed daily, snapshot 2026-07-22.