GraphARC - Output Graph Edge Count: leaderboard
Metric: Accuracy (%) of answers to questions about the number of edges of the output graph that the inferred transformation produces (the model never sees that output), GraphARC few-shot graph-transformation tasks (21 transformations; the model sees a few input-output graph pairs and a test input graph of 5 to 15 nodes encoded as an adjacency or incidence list), answer compared with the value computed from the true output graph; the OpenAI reasoning models ran one system prompt at medium reasoning effort, the other models four system-prompt variants; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 98 |
| 2 | O4 Mini | 98 |
| 3 | O3 Mini | 94 |
| 4 | O1 Mini | 76 |
| 5 | Qwen 3 14B | 67 |
| 6 | Qwen 3 8B | 61 |
| 7 | Qwen 3 32B | 55 |
| 8 | Qwen 3 4B | 54 |
| 9 | GPT-4.1 Nano | 46 |
| 10 | Qwen 3 1.7B | 27 |
| 11 | Llama 3.1 8B | 11 |
| 12 | DeepSeek R1 Distill Llama 8B | 11 |
| 13 | Llama 3 8B | 6 |
| 14 | Mistral-7B-v0.2 | 4 |
| 15 | OLMo 2 7B | 4 |
Interactive version: theaggregate.ai/benchmark?slug=grapharc-output-graph-edge-count · How It Works · Data refreshed daily, snapshot 2026-10-07.