MHRC-Bench (Preceding Context) - HLS: leaderboard

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

Top models

#ModelScore
1Gemini 2.5 Pro18
2GPT-512.1
3DeepSeek V3.29.9
4Grok 49

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