GraphARC - Output Graph Is Tree: leaderboard
GraphARC (2026) carries the few-shot transformation format of the Abstraction and Reasoning Corpus to graphs; this question asks for whether it is a tree of the output graph that the inferred transformation would produce. Accuracy in percent over small test graphs; higher is better.
Metric: Accuracy (%) of answers to questions about whether the graph is a tree 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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 Mini | 99 | #546 |
| 2 | GPT-5 | 98 | #178 |
| 3 | O4 Mini | 98 | #368 |
| 4 | O1 Mini | 93 | #750 |
| 5 | Qwen 3 14B | 70 | #1269 |
| 6 | Qwen 3 8B | 67 | #1873 |
| 7 | GPT-4.1 Nano | 64 | #2056 |
| 8 | Qwen 3 1.7B | 58 | #5860 |
| 9 | OLMo 2 7B | 58 | #8320 |
| 10 | Llama 3 8B | 55 | #5900 |
| 11 | Llama 3.1 8B | 53 | #5196 |
| 12 | Qwen 3 32B | 50 | #972 |
| 13 | Qwen 3 4B | 45 | #2348 |
| 14 | Mistral-7B-v0.2 | 44 | #7596 |
| 15 | DeepSeek R1 Distill Llama 8B | 32 | #7059 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=grapharc-output-graph-is-tree · How It Works · Data refreshed daily, snapshot 2026-11-21.