GraphInstruct (Generation) - L1 Single Constraint: leaderboard
GraphInstruct (Generation) L1 Single Constraint scores zero-shot graph generation on the 200 GraphInstruct (2026) instructions whose graphs must satisfy a single explicit constraint (graph type). 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 200 GraphInstruct instructions of level L1, which requires a single explicit constraint (graph type); 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: Estimated already saturated. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4 (20250514) | 98.3 | #405 |
| 2 | GPT-4o | 98.2 | #751 |
| 3 | Qwen 3.5 122B A10B | 98 | #346 |
| 4 | Qwen 3.5 397B A17B | 97.9 | #264 |
| 5 | Claude Sonnet 4.6 | 97.7 | #173 |
| 6 | GraphInstruct DeepSeek-V3 (checkpoint unspecified) | 97.7 | |
| 7 | GPT-4.1 | 96.8 | #505 |
| 8 | Qwen 3.5 35B A3B | 95.5 | #492 |
| 9 | Llama 3.3 70B Instruct | 94.8 | #1385 |
| 10 | GPT-3.5 Turbo | 90.5 | #3005 |
| 11 | GPT-4o Mini | 89.8 | #1667 |
| 12 | Llama 3.1 8B Instruct | 73 | #4600 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=graphinstruct-generation-l1-single-constraint · How It Works · Data refreshed daily, snapshot 2026-11-21.