LLVM-Bench (Trae Agent): leaderboard

Metric: Resolved rate (%; share of the 423 validated LLVM issues, versions 18-21, whose generated patch applies, builds and passes the full LLVM test suite including the issue tests in LLVM-Gym; Trae Agent scaffold with at most 50 interaction turns, temperature 0, 8,192-token generation limit). Source: arxiv.org. Saturation forecast: Around 2030. 4 models tracked.

Top models

#ModelScore
1DeepSeek V3.28.98
2Grok Code Fast 17.33
3Gemini 3 Flash4.49
4Qwen 3 Coder Plus3.55

Interactive version: theaggregate.ai/benchmark?slug=llvm-bench-trae-agent · How It Works · Data refreshed daily, snapshot 2026-09-29.