reasoning benchmark
RepoQA
RepoQA is a benchmark for evaluating long-context code understanding capabilities of Large Language Models through the Searching Needle Function (SNF) task, where LLMs must locate specific functions in code repositories using natural language descriptions. The benchmark contains 500 code search tasks spanning 50 repositories across 5 modern programming languages (Python, Java, TypeScript, C++, and Rust), tested on 26 general and code-specific LLMs to assess their ability to comprehend and navigate code repositories.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
RepoQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 85.0% | 100.0% | 2 | C | |
| 2 | MI | 77.0% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
RepoQA highlights
The top published results on this benchmark's own scale.
What is RepoQA?
Definition and scoring fields from the benchmark registry.
RepoQA is a benchmark for evaluating long-context code understanding capabilities of Large Language Models through the Searching Needle Function (SNF) task, where LLMs must locate specific functions in code repositories using natural language descriptions. The benchmark contains 500 code search tasks spanning 50 repositories across 5 modern programming languages (Python, Java, TypeScript, C++, and Rust), tested on 26 general and code-specific LLMs to assess their ability to comprehend and navigate code repositories.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- RepoQA
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- repoqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about RepoQA.
Which model scores highest on RepoQA?
Phi-3.5-MoE-instruct is currently ranked first with 85.0%.
What does RepoQA measure?
RepoQA is a benchmark for evaluating long-context code understanding capabilities of Large Language Models through the Searching Needle Function (SNF) task, where LLMs must locate specific functions in code repositories using natural language descriptions. The benchmark contains 500 code search tasks spanning 50 repositories across 5 modern programming languages (Python, Java, TypeScript, C++, and Rust), tested on 26 general and code-specific LLMs to assess their ability to comprehend and navigate code repositories.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.