GraphARC: leaderboard
Relational reasoning lies at the heart of intelligence, but existing benchmarks are typically confined to formats such as grids or text. We introduce GraphARC, a benchmark for abstract reasoning on graph-structured data. GraphARC generalizes the few-shot transformation learning paradigm of the Abstraction and Reasoning Corpus (ARC). Each task requires inferring a transformation rule from a few inp
Metric: Average accuracy (self-reported). Source: benchmarklist.com. Saturation forecast: Around December 2026. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 91 | #98 |
| 2 | O4 Mini | 87 | #180 |
| 3 | O3 Mini | 81 | #272 |
| 4 | O1 Mini | 58 | #323 |
| 5 | Qwen 3 14B | 37 | #537 |
| 6 | Qwen 3 32B | 34 | #443 |
| 7 | GPT-4.1 Nano | 12 | #731 |
| 8 | Llama 3.1 8B | 9 | #1151 |
| 9 | Mistral-7B-v0.2 | 2 | #1388 |
| 10 | OLMo 2 7B | 1 | #1371 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=grapharc · How It Works · Data refreshed daily, snapshot 2026-10-20.