GraphInstruct (Generation) - L5 Multi-Step Graph Editing: leaderboard
GraphInstruct (Generation) L5 Multi-Step Graph Editing scores zero-shot graph generation on the 50 GraphInstruct (2026) instructions whose graphs must satisfy ordered edits to a base graph. The level quality score, 0 to 100 and higher is better, is computed by code from validity, distribution match, reference similarity and constraint satisfaction.
Metric: Level quality score (0-100; the paper's 0-1 score times 100) on the 50 GraphInstruct instructions of level L5, which requires ordered edits to a base graph; zero-shot prompting; five generations per instruction at temperature 0.7 with the InstructGraph code-style prefix; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 84.1 | #179 |
| 2 | GPT-4o | 82.3 | #754 |
| 3 | Qwen 3.5 397B A17B | 82.1 | #270 |
| 4 | Qwen 3.5 122B A10B | 81.4 | #350 |
| 5 | Claude Sonnet 4 (20250514) | 80.6 | #410 |
| 6 | GraphInstruct DeepSeek-V3 (checkpoint unspecified) | 79.9 | |
| 7 | Llama 3.3 70B Instruct | 79.4 | #1394 |
| 8 | Qwen 3.5 35B A3B | 78 | #494 |
| 9 | GPT-4.1 | 77.9 | #506 |
| 10 | GPT-3.5 Turbo | 75.2 | #3076 |
| 11 | GPT-4o Mini | 75 | #1680 |
| 12 | Llama 3.1 8B Instruct | 72.7 | #4655 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=graphinstruct-generation-l5-multi-step-graph-editing · How It Works · Data refreshed daily, snapshot 2026-11-22.