general benchmark
Aider-Polyglot Edit
A challenging multi-language coding benchmark that evaluates models' code editing abilities across C++, Go, Java, JavaScript, Python, and Rust. Contains 225 of Exercism's most difficult programming problems, selected as problems that were solved by 3 or fewer out of 7 top coding models. The benchmark focuses on code editing tasks and measures both correctness of solutions and proper edit format usage. Designed to re-calibrate evaluation scales so top models score between 5-50%.
Updated Aug 7, 2026
Published models10
Registry coverage10
MetricScore
EvidenceB
Aider-Polyglot Edit leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | DE | 79.7% | 100.0% | 10 | C | |
| 2 | GO | 72.7% | 88.9% | 10 | C | |
| 3 | OP | 60.4% | 77.8% | 10 | C | |
| 4 | OP | 58.2% | 66.7% | 10 | C | |
| 5 | GO | 56.7% | 55.6% | 10 | C | |
| 6 | OP | 52.9% | 44.4% | 10 | C | |
| 7 | OP | 44.9% | 33.3% | 10 | C | |
| 8 | OP | 31.6% | 22.2% | 10 | C | |
| 9 | OP | 18.2% | 11.1% | 10 | C | |
| 10 | OP | 6.2% | 0.0% | 10 | C |
Score distribution
Top published rows on the benchmark's original scale.
Aider-Polyglot Edit highlights
The top published results on this benchmark's own scale.
What is Aider-Polyglot Edit?
Definition and scoring fields from the benchmark registry.
A challenging multi-language coding benchmark that evaluates models' code editing abilities across C++, Go, Java, JavaScript, Python, and Rust. Contains 225 of Exercism's most difficult programming problems, selected as problems that were solved by 3 or fewer out of 7 top coding models. The benchmark focuses on code editing tasks and measures both correctness of solutions and proper edit format usage. Designed to re-calibrate evaluation scales so top models score between 5-50%.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Aider-Polyglot Edit
- Modality
- text
- Primary category
- general
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- aider-polyglot-edit|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Aider-Polyglot Edit.
Which model scores highest on Aider-Polyglot Edit?
DeepSeek-V3 is currently ranked first with 79.7%.
What does Aider-Polyglot Edit measure?
A challenging multi-language coding benchmark that evaluates models' code editing abilities across C++, Go, Java, JavaScript, Python, and Rust. Contains 225 of Exercism's most difficult programming problems, selected as problems that were solved by 3 or fewer out of 7 top coding models. The benchmark focuses on code editing tasks and measures both correctness of solutions and proper edit format usage. Designed to re-calibrate evaluation scales so top models score between 5-50%.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
10 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.