reasoning benchmark
RepoBench Leaderboard
RepoBench evaluates repository-level code auto-completion systems through retrieval, cross-file and in-file code completion, and a combined retrieval-and-prediction pipeline for Python and Java.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
RepoBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score34.00% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
RepoBench Highlights
The leading models and scores on this benchmark.
The Top AI Models for RepoBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis repobench AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MAMistral AI
- Score
- 34.00%
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures RepoBench, not total model capability
Selection summary
Best AI Models for RepoBench
Codestral-22B currently leads RepoBench with 34.00%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is RepoBench?
What RepoBench measures and how its scores work.
RepoBench is a benchmark comprising RepoBench-R for retrieving relevant code snippets across files, RepoBench-C for code completion using cross-file and in-file context, and RepoBench-P for a pipeline combining retrieval and prediction.
RepoBench reports Score as a ratio for repository-level code auto-completion across its three tasks.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- RepoBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about RepoBench.
Which model scores highest on RepoBench?
Codestral-22B is currently ranked first with 34.00%.
What are the top three models on RepoBench?
The current leaders are Codestral-22B (34.00%).
Which RepoBench model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among RepoBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.