reasoning benchmark
RSI Index
The RSI (Recursive Self-Improvement) Index is OpenAI's aggregate metric across a bundle of internal AI-research evaluations, including debugging research systems, optimizing kernels and training recipes, and improving other models, measuring progress toward recursive self-improvement.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
RSI Index Ranking
Higher score ranks better on this benchmark.
| 1 | OP | 57.9% | 100.0% | 3 | C | |
| 2 | OP | 56.3% | 50.0% | 3 | C | |
| 3 | OP | 41.9% | 0.0% | 3 | C |
RSI Index Score Distribution
A closer view of the leading scores on this benchmark.
RSI Index Highlights
The leading models and scores on this benchmark.
What is RSI Index?
What RSI Index measures and how its scores work.
The RSI (Recursive Self-Improvement) Index is OpenAI's aggregate metric across a bundle of internal AI-research evaluations, including debugging research systems, optimizing kernels and training recipes, and improving other models, measuring progress toward recursive self-improvement.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- RSI Index
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- rsi-index|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about RSI Index.
Which model scores highest on RSI Index?
GPT-5.6 Sol is currently ranked first with 57.9%.
What does RSI Index measure?
The RSI (Recursive Self-Improvement) Index is OpenAI's aggregate metric across a bundle of internal AI-research evaluations, including debugging research systems, optimizing kernels and training recipes, and improving other models, measuring progress toward recursive self-improvement.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.