agents benchmark
KernelGen 1P Leaderboard
KernelGen 1P is an OpenAI AI-self-improvement evaluation that measures whether models can write and optimize compute kernels.
Updated Oct 23, 2026
Models3
Model coverage3
MetricScore
EvidenceB
KernelGen 1P Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score61.10% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score49.20% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score22.40% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
KernelGen 1P Highlights
The leading models and scores on this benchmark.
KernelGen 1P Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for KernelGen 1P
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is KernelGen 1P?
What KernelGen 1P measures and how its scores work.
KernelGen 1P is an OpenAI AI-self-improvement evaluation and part of a suite tracking progress toward accelerating internal research.
It measures whether models can write and optimize compute kernels, reported as Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- KernelGen 1P
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about KernelGen 1P.
Which model scores highest on KernelGen 1P?
GPT-5.6 Sol is currently ranked first with 61.10%.
What are the top three models on KernelGen 1P?
The current leaders are GPT-5.6 Sol (61.10%), GPT-5.6 Terra (49.20%), and GPT-5.6 Luna (22.40%).
Which KernelGen 1P model has the lowest official input price?
GPT-5.6 Luna has the lowest matched official input price at $0.20 input / $1.2 output per 1M tokens.
Which models are fastest among KernelGen 1P results?
The fastest matched records are GPT-5.6 Luna (215.52 tok/s via OpenAI), GPT-5.6 Terra (43.35 tok/s via OpenAI), and GPT-5.6 Sol (25.46 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.