reasoning benchmark
RepoBench
RepoBench is a benchmark for evaluating repository-level code auto-completion systems through three interconnected tasks: RepoBench-R (retrieval of relevant code snippets across files), RepoBench-C (code completion with cross-file and in-file context), and RepoBench-P (pipeline combining retrieval and prediction). Supports Python and Java programming languages and addresses the gap in evaluating real-world, multi-file programming scenarios by providing a more complete comparison of performance in auto-completion systems.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
RepoBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 34.0% | 100.0% | 1 | C |
RepoBench highlights
The top published results on this benchmark's own scale.
What is RepoBench?
Definition and scoring fields from the benchmark registry.
RepoBench is a benchmark for evaluating repository-level code auto-completion systems through three interconnected tasks: RepoBench-R (retrieval of relevant code snippets across files), RepoBench-C (code completion with cross-file and in-file context), and RepoBench-P (pipeline combining retrieval and prediction). Supports Python and Java programming languages and addresses the gap in evaluating real-world, multi-file programming scenarios by providing a more complete comparison of performance in auto-completion systems.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- RepoBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- repobench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about RepoBench.
Which model scores highest on RepoBench?
Codestral-22B is currently ranked first with 34.0%.
What does RepoBench measure?
RepoBench is a benchmark for evaluating repository-level code auto-completion systems through three interconnected tasks: RepoBench-R (retrieval of relevant code snippets across files), RepoBench-C (code completion with cross-file and in-file context), and RepoBench-P (pipeline combining retrieval and prediction). Supports Python and Java programming languages and addresses the gap in evaluating real-world, multi-file programming scenarios by providing a more complete comparison of performance in auto-completion systems.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.