MHRC-Bench (Full Context) - Chisel: leaderboard

Metric: Exact match (%; repository-level completion of syntactically complete Chisel 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

#ModelScore
1Gemini 2.5 Pro33.2
2GPT-524.8
3DeepSeek V3.222.6
4Grok 422.4

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