MHRC-Bench (Full Context) - HLS: leaderboard
Metric: Exact match (%; repository-level completion of syntactically complete high-level-synthesis C/C++ code units given the preceding and following code in a 2,048-token prompt, no retrieval). Source: arxiv.org. Saturation forecast: Around December 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 34.6 |
| 2 | Grok 4 | 31.6 |
| 3 | GPT-5 | 31.4 |
| 4 | DeepSeek V3.2 | 30.3 |
Interactive version: theaggregate.ai/benchmark?slug=mhrc-bench-full-context-hls · How It Works · Data refreshed daily, snapshot 2026-09-25.