general benchmark
Aider-Polyglot Leaderboard
A coding benchmark that evaluates LLMs on 225 challenging Exercism programming exercises across C++, Go, Java, JavaScript, Python, and Rust. Models receive two attempts to solve each problem, with test error feedback provided after the first attempt if it fails. The benchmark measures both initial problem-solving ability and capacity to edit code based on error feedback, providing an end-to-end evaluation of code generation and editing capabilities across multiple programming languages.
Updated Aug 17, 2026
Models22
Model coverage22
MetricScore
EvidenceB
Aider-Polyglot Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score88.0% | Percentile100.0% | Participants22 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score82.2% | Percentile95.2% | Participants22 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score81.3% | Percentile90.5% | Participants22 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score76.5% | Percentile85.7% | Participants22 | EvidenceC | Evaluated |
| Rank05 | ModelDE | Score74.5% | Percentile81.0% | Participants22 | EvidenceC | Evaluated |
| Rank06 | ModelDE | Score71.6% | Percentile76.2% | Participants22 | EvidenceC | Evaluated |
| Rank07 | ModelOP | Score68.9% | Percentile71.4% | Participants22 | EvidenceC | Evaluated |
| Rank08 | ModelDE | Score68.4% | Percentile66.7% | Participants22 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score66.7% | Percentile61.9% | Participants22 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score61.9% | Percentile57.1% | Participants22 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score61.8% | Percentile52.4% | Participants22 | EvidenceC | Evaluated |
| Rank12 | ModelMA | Score60.0% | Percentile47.6% | Participants22 | EvidenceC | Evaluated |
| Rank13 | ModelMA | Score60.0% | Percentile42.9% | Participants22 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score57.3% | Percentile38.1% | Participants22 | EvidenceC | Evaluated |
| Rank15 | ModelOP | Score51.6% | Percentile33.3% | Participants22 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score49.8% | Percentile28.6% | Participants22 | EvidenceC | Evaluated |
| Rank17 | ModelDE | Score49.6% | Percentile23.8% | Participants22 | EvidenceC | Evaluated |
| Rank18 | ModelMA | Score47.1% | Percentile19.1% | Participants22 | EvidenceC | Evaluated |
| Rank19 | ModelOP | Score34.7% | Percentile14.3% | Participants22 | EvidenceC | Evaluated |
| Rank20 | ModelOP | Score30.7% | Percentile9.5% | Participants22 | EvidenceC | Evaluated |
| Rank21 | ModelGO | Score26.7% | Percentile4.8% | Participants22 | EvidenceC | Evaluated |
| Rank22 | ModelOP | Score9.8% | Percentile0.0% | Participants22 | EvidenceC | Evaluated |
Aider-Polyglot Highlights
The leading models and scores on this benchmark.
Aider-Polyglot Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Aider-Polyglot
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis aider-polyglot 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.
- 01OPGPT-5OpenAI
- Score
- 88.0%
- Price
- $1.3 input / $10 output per 1M tokens
- Speed
- Up to 100 tok/s via OpenAI
Strengths
- Ranks #1 of 22 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Aider-Polyglot, not total model capability
- 02GO
- Score
- 82.2%
- Price
- $1.3 input / $10 output per 1M tokens
- Speed
- Up to 85 tok/s via Google
Strengths
- Ranks #2 of 22 compared models
- 95th percentile on this benchmark
- C evidence result
Considerations
- This result measures Aider-Polyglot, not total model capability
- 03OPo3OpenAI
- Score
- 81.3%
- Price
- $2.0 input / $8.0 output per 1M tokens
- Speed
- Up to 50 tok/s via OpenAI
Strengths
- Ranks #3 of 22 compared models
- 90th percentile on this benchmark
- C evidence result
Considerations
- This result measures Aider-Polyglot, not total model capability
- 04GOGemini 2.5 ProGoogle
- Score
- 76.5%
- Price
- $1.3 input / $10 output per 1M tokens
- Speed
- Up to 86 tok/s via Google
Strengths
- Ranks #4 of 22 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures Aider-Polyglot, not total model capability
- 05DEDeepSeek-V3.2-ExpDeepSeek
- Score
- 74.5%
- Price
- $0.14 input / $0.28 output per 1M tokens
- Speed
- Up to 97 tok/s via DeepInfra
Strengths
- Ranks #5 of 22 compared models
- 81th percentile on this benchmark
- C evidence result
Considerations
- This result measures Aider-Polyglot, not total model capability
Selection summary
Best AI Models for Aider-Polyglot
GPT-5 currently leads Aider-Polyglot with 88.0%. 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 Aider-Polyglot?
What Aider-Polyglot measures and how its scores work.
A coding benchmark that evaluates LLMs on 225 challenging Exercism programming exercises across C++, Go, Java, JavaScript, Python, and Rust. Models receive two attempts to solve each problem, with test error feedback provided after the first attempt if it fails. The benchmark measures both initial problem-solving ability and capacity to edit code based on error feedback, providing an end-to-end evaluation of code generation and editing capabilities across multiple programming languages.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Aider-Polyglot
- Modality
- text
- Primary category
- general
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- aider-polyglot|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Aider-Polyglot.
Which model scores highest on Aider-Polyglot?
GPT-5 is currently ranked first with 88.0%.
What does Aider-Polyglot measure?
A coding benchmark that evaluates LLMs on 225 challenging Exercism programming exercises across C++, Go, Java, JavaScript, Python, and Rust. Models receive two attempts to solve each problem, with test error feedback provided after the first attempt if it fails. The benchmark measures both initial problem-solving ability and capacity to edit code based on error feedback, providing an end-to-end evaluation of code generation and editing capabilities across multiple programming languages.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
22 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.