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

#ModelScore
1Claude 3.7 Sonnet31.9
2Gemini 2.0 Flash (001)18.4
3Llama 3.3 70B Instruct1.9
4GPT-4o Mini1

Interactive version: theaggregate.ai/benchmark?slug=complexity-ceiling-benchmark · How It Works · Data refreshed daily, snapshot 2026-09-26.