MHRC-Bench (Preceding Context) - Chisel: leaderboard

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

Top models

#ModelScore
1GPT-515.2
2Gemini 2.5 Pro11.1
3DeepSeek V3.210.3
4Grok 410.2

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