Complexity Ceiling Benchmark: leaderboard
Metric: Accuracy (%; share of parseable trials whose final answer and every intermediate step are exact, 40 seeded trials at each depth N = 5, 10, ..., 50; temperature 0 via OpenRouter; mean of the three domain accuracies, 1,200 trials per model). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.7 Sonnet | 31.9 |
| 2 | Gemini 2.0 Flash (001) | 18.4 |
| 3 | Llama 3.3 70B Instruct | 1.9 |
| 4 | GPT-4o Mini | 1 |
Interactive version: theaggregate.ai/benchmark?slug=complexity-ceiling-benchmark · How It Works · Data refreshed daily, snapshot 2026-09-26.