PaperBench

PaperBench is a benchmark for how well a model works as an autonomous coding agent. The official description says: "PaperBench - evaluated in the BasicAgent setting under Code-Dev mode, judged by Claude Opus 4.6, averaged over 3 runs (max 12 hours per run)". Below we describe in simple words what benchmarks of this type generally examine.

PaperBench measures how well a model works as an autonomous coding agent. In detail, it checks:

• fixing real, open bugs from real software repositories
• planning multi-step changes, running commands and editing files by itself
• passing the project's test suite after its changes
• handling whole repositories, not just small isolated code snippets

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: PaperBench - evaluated in the BasicAgent setting under Code-Dev mode, judged by Claude Opus 4.6, averaged over 3 runs (max 12 hours per run).

What is the PaperBench benchmark?

PaperBench is a benchmark for how well a model works as an autonomous coding agent. The official description says: 'PaperBench - evaluated in the BasicAgent setting under Code-Dev mode, judged by Claude Opus 4.6, averaged over 3 runs (max 12 hours per run)'. Below we describe in simple words what benchmarks of this type generally examine.

What does PaperBench test?

PaperBench mainly measures how well a model works as an autonomous coding agent. Concretely, it checks: fixing real, open bugs from real software repositories; planning multi-step changes, running commands and editing files by itself; passing the project's test suite after its changes.

How is the PaperBench score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Where do I get PaperBench data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/paperbench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.