All benchmarks

RSI Index

Paper

Progress Over Time

Interactive timeline showing model performance evolution on RSI Index

State-of-the-art frontier
Open
Proprietary

RSI Index Leaderboard

3 models
ContextCostLicense
1
OpenAI
GPT-5.6 SolNew
OpenAI
—1.1M$5.00 / $30.00
2
OpenAI
GPT-5.6 TerraNew
OpenAI
—1.1M$2.50 / $15.00
3
OpenAI
GPT-5.6 LunaNew
OpenAI
—1.1M$1.00 / $6.00
Notice missing or incorrect data?
About this benchmark

What is 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.

RSI Index is a text benchmark evaluating models on reasoning, agents, code, and systems tasks. LLM Stats tracks 3 models on this benchmark, scored on a 0–1 scale. The current average is 0.5, with the leader at 0.6.

Compare leaders on the best AI for reasoning, best AI for agents, best AI for code and best AI for systems leaderboards.

Current leaders

GPT-5.6 Sol from OpenAI currently leads the RSI Index leaderboard with a score of 0.579 across 3 evaluated AI models.

1GPT-5.6 SolOpenAI57.9%
2GPT-5.6 TerraOpenAI56.3%
3GPT-5.6 LunaOpenAI41.9%

FAQ

Common questions about the RSI Index benchmark and leaderboard.

What is the RSI Index benchmark?

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.

What is the RSI Index leaderboard?

The RSI Index leaderboard ranks 3 AI models based on their performance on this benchmark. Currently, GPT-5.6 Sol by OpenAI leads with a score of 0.579. The average score across all models is 0.520.

What is the highest RSI Index score?

The highest RSI Index score is 0.579, achieved by GPT-5.6 Sol from OpenAI.

How many models are evaluated on RSI Index?

3 models have been evaluated on the RSI Index benchmark, with 0 verified results and 3 self-reported results.

Where can I find the RSI Index paper?

The RSI Index paper is available at https://openai.com/index/gpt-5-6/. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does RSI Index cover?

RSI Index is categorized under reasoning, agents, code, and systems. The benchmark evaluates text models.

Which model offers the best value on RSI Index?

Among models scoring within 10% of the leader, GPT-5.6 Terra from OpenAI is the cheapest, at $2.50 per million input tokens with a score of 0.563.

How recent are the RSI Index leaderboard results?

The RSI Index leaderboard was last updated in July 2026 and currently includes 3 evaluated models.