PCB-Bench - Routing Micro QA SBERT: leaderboard
Metric: SBERT similarity (%). Source: digailab.github.io. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.1 | 57.38 |
| 2 | DeepSeek V3.1 | 56.57 |
| 3 | GPT-4o | 56.47 |
| 4 | Llama 4 Maverick | 55.64 |
| 5 | Ministral 3B | 55.52 |
| 6 | InternVL3-78B | 55.11 |
| 7 | MythoMax-L2-13B | 51.73 |
| 8 | GPT-5 | 51.37 |
| 9 | Gemini 2.5 Pro | 48.4 |
| 10 | Qwen 2.5 7B Instruct | 20.81 |
Interactive version: theaggregate.ai/benchmark?slug=pcb-bench-routing-micro-qa-sbert · How It Works · Data refreshed daily, snapshot 2026-09-05.