agents benchmark
NL2Repo Leaderboard
NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.
Updated Aug 17, 2026
Models17
Model coverage17
MetricScore
EvidenceB
NL2Repo Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelDE | Score61.5% | Percentile100.0% | Participants17 | EvidenceC | Evaluated |
| Rank02 | ModelZA | Score58.0% | Percentile93.8% | Participants17 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score55.9% | Percentile87.5% | Participants17 | EvidenceC | Evaluated |
| Rank04 | ModelDE | Score54.2% | Percentile81.3% | Participants17 | EvidenceC | Evaluated |
| Rank05 | ModelZA | Score48.9% | Percentile75.0% | Participants17 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score47.2% | Percentile68.8% | Participants17 | EvidenceC | Evaluated |
| Rank07 | ModelBY | Score47.0% | Percentile62.5% | Participants17 | EvidenceC | Evaluated |
| Rank08 | ModelTE | Score45.6% | Percentile56.3% | Participants17 | EvidenceC | Evaluated |
| Rank09 | ModelBY | Score43.7% | Percentile50.0% | Participants17 | EvidenceC | Evaluated |
| Rank10 | ModelZA | Score42.7% | Percentile43.8% | Participants17 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score42.3% | Percentile37.5% | Participants17 | EvidenceC | Evaluated |
| Rank12 | ModelMI | Score42.1% | Percentile31.3% | Participants17 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score41.1% | Percentile25.0% | Participants17 | EvidenceC | Evaluated |
| Rank14 | ModelMI | Score39.8% | Percentile18.8% | Participants17 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score37.9% | Percentile12.5% | Participants17 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score36.2% | Percentile6.3% | Participants17 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score29.4% | Percentile0.0% | Participants17 | EvidenceC | Evaluated |
NL2Repo Highlights
The leading models and scores on this benchmark.
NL2Repo Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for NL2Repo
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis nl2repo AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01DEDeepSeek-V4-Pro-0813DeepSeek
- Score
- 61.5%
- Price
- $0.43 input / $0.87 output per 1M tokens
- Speed
- Up to 33 tok/s via DeepSeek
Strengths
- Ranks #1 of 17 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures NL2Repo, not total model capability
- 02ZAGLM-5.3Zhipu AI
- Score
- 58.0%
Strengths
- Ranks #2 of 17 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures NL2Repo, not total model capability
- 03ACQwen3.8 MaxAlibaba Cloud / Qwen Team
- Score
- 55.9%
- Price
- $2.0 input / $6.0 output per 1M tokens
Strengths
- Ranks #3 of 17 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures NL2Repo, not total model capability
- 04DEDeepSeek-V4-Flash-0731DeepSeek
- Score
- 54.2%
- Price
- $0.14 input / $0.28 output per 1M tokens
- Speed
- Up to 19 tok/s via Novita
Strengths
- Ranks #4 of 17 compared models
- 81th percentile on this benchmark
- C evidence result
Considerations
- This result measures NL2Repo, not total model capability
- 05ZAGLM-5.2Zhipu AI
- Score
- 48.9%
- Price
- $1.4 input / $4.4 output per 1M tokens
Strengths
- Ranks #5 of 17 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures NL2Repo, not total model capability
Selection summary
Best AI Models for NL2Repo
DeepSeek-V4-Pro-0813 currently leads NL2Repo with 61.5%. 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 NL2Repo?
What NL2Repo measures and how its scores work.
NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- NL2Repo
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- nl2repo|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about NL2Repo.
Which model scores highest on NL2Repo?
DeepSeek-V4-Pro-0813 is currently ranked first with 61.5%.
What does NL2Repo measure?
NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
17 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.