GraphARC - Output Graph Node Count: leaderboard

GraphARC (2026) carries the few-shot transformation format of the Abstraction and Reasoning Corpus to graphs; this question asks for its number of nodes 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 the number of nodes 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

#ModelScoreOverall rank
1O3 Mini83#546
2O4 Mini69#368
3O1 Mini63#750
4Qwen 3 8B62#1873
5GPT-561#178
6GPT-4.1 Nano49#2056
7Qwen 3 32B49#972
8Qwen 3 14B39#1269
9Qwen 3 1.7B39#5860
10Llama 3.1 8B32#5196
11Qwen 3 4B30#2348
12Mistral-7B-v0.219#7596
13OLMo 2 7B19#8320
14DeepSeek R1 Distill Llama 8B15#7059
15Llama 3 8B12#5900

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-node-count · How It Works · Data refreshed daily, snapshot 2026-11-21.