AgentKernelArena - PyTorch-to-HIP: leaderboard

Metric: Mean speedup (x; arithmetic mean over the 24 PyTorch-to-HIP tasks of the per-task speedup of the agent-written HIP kernel over PyTorch eager execution, counting 0 for a task whose kernel fails compilation or correctness; per-task mean of 3 runs; agent in an isolated workspace, 3600 s timeout, up to 3 kernel versions; AMD Instinct MI300X). Source: arxiv.org. Saturation forecast: Rough model projection: around 2027. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.6 (Claude Code)6.7
2Claude Sonnet 4.6 (Claude Code)5.3

Interactive version: theaggregate.ai/benchmark?slug=agentkernelarena-pytorch-to-hip · How It Works · Data refreshed daily, snapshot 2026-09-26.