code benchmark
Codegolf v2.2
Codegolf v2.2 benchmark
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
Codegolf v2.2 Ranking
Higher score ranks better on this benchmark.
| 01 | GO | 16.8% | 100.0% | 4 | C | |
| 02 | GO | 16.8% | 66.7% | 4 | C | |
| 03 | GO | 11.0% | 33.3% | 4 | C | |
| 04 | GO | 11.0% | 0.0% | 4 | C |
Codegolf v2.2 Score Distribution
A closer view of the leading scores on this benchmark.
Codegolf v2.2 Highlights
The leading models and scores on this benchmark.
What is Codegolf v2.2?
What Codegolf v2.2 measures and how its scores work.
Codegolf v2.2 benchmark
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Codegolf v2.2
- Modality
- text
- Primary category
- code
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- codegolf-v2.2|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Codegolf v2.2.
Which model scores highest on Codegolf v2.2?
Gemma 3n E4B Instructed is currently ranked first with 16.8%.
What does Codegolf v2.2 measure?
Codegolf v2.2 benchmark
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.