RTL-BenchLS - Round-Trip NL Spec (r=0.5): leaderboard

Metric: Functional pass rate (%) on round-trip reasoning on 420 designs (slice 1 of RTL-BenchLS): the model compresses a Verilog design into an intermediate abstract, then regenerates the RTL from its own abstract, the abstract a natural-language specification at most 0.5 times the design length; functional pass rate (%; output formally equivalent to the golden design, Cadence Conformal LEC for combinational and JasperGold SEC for sequential designs), temperature 0.2; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.517.1
2GPT-4o11.7
3Claude Haiku 4.511.7
4GPT-4o Mini11.3
5DeepSeek V3.210.3
6Qwen 3.5 397B A17B4.6
7Llama 3.3 70B Instruct1.9

Interactive version: theaggregate.ai/benchmark?slug=rtl-benchls-round-trip-nl-spec-r-0-5 · How It Works · Data refreshed daily, snapshot 2026-09-29.