MHRC-Bench (Full Context) - Verilog/SystemVerilog: leaderboard
Metric: Exact match (%; repository-level completion of syntactically complete Verilog or SystemVerilog code units given the preceding and following code in a 2,048-token prompt, no retrieval). Source: arxiv.org. Saturation forecast: Around October 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 34.5 |
| 2 | Gemini 2.5 Pro | 33.2 |
| 3 | Grok 4 | 31.4 |
| 4 | DeepSeek V3.2 | 28.7 |
Interactive version: theaggregate.ai/benchmark?slug=mhrc-bench-full-context-verilog-systemverilog · How It Works · Data refreshed daily, snapshot 2026-09-25.