MHRC-Bench (Preceding Context) - VHDL: leaderboard

Metric: Exact match (%; repository-level completion of syntactically complete VHDL code units given the preceding code only in a 2,048-token prompt, no retrieval). Source: arxiv.org. Saturation forecast: Around January 2028. 4 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro23.3
2GPT-520.8
3DeepSeek V3.217
4Grok 410.4

Interactive version: theaggregate.ai/benchmark?slug=mhrc-bench-preceding-context-vhdl · How It Works · Data refreshed daily, snapshot 2026-09-25.