LLM Self-Modeling - With Logit Estimation: leaderboard
Metric: Skill above dummy predictor (-1 to 1, higher is better; 4096-token thinking budget where enabled). Source: arxiv.org. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.1 (Thinking) | 0.12 |
| 2 | Qwen 3.5 35B A3B (Thinking) | 0.09 |
| 3 | Qwen 3 8B (Thinking) | 0.09 |
| 4 | Qwen 3.5 4B (Thinking) | 0.07 |
| 5 | Llama 3.3 70B Instruct | 0.05 |
| 6 | GPT-OSS-20B (High) | 0.04 |
| 7 | Llama 3.1 8B Instruct | -0.02 |
Interactive version: theaggregate.ai/benchmark?slug=llm-self-modeling-with-logit-estimation · How It Works · Data refreshed daily, snapshot 2026-09-19.