ResearchEnvBench - Single-GPU Execution: leaderboard
Metric: Success rate (%) of the single-GPU run of the entry point (C3) on the 43 applicable repositories, ResearchEnvBench's 44 post-2024 ML research repositories: the agent starts from a bare Ubuntu container with CUDA 12.4 drivers and two RTX 4090 GPUs, sets up the environment with shell and file-editing tools under a time budget, and hidden probes then check the frozen environment; repositories where the stage does not apply are left out of the denominator; higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-4.7 | 48.8 | #185 |
| 2 | GPT-5.1 Codex | 44.2 | #154 |
| 3 | Claude Sonnet 4.5 | 41.9 | #138 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=researchenvbench-single-gpu-execution · How It Works · Data refreshed daily, snapshot 2026-10-11.