GraphInstruct (Generation, Few-Shot): leaderboard
GraphInstruct (Generation, Few-Shot) scores instruction-following graph generation on the 800 GraphInstruct (2026) instructions under few-shot prompting with three same-level demonstrations. The quality score, 0 to 100 and higher is better, is computed by code from validity, distribution match, reference similarity and constraint satisfaction across six constraint levels.
Metric: Quality S_total (0-100; the paper's 0-1 score times 100): level scores weighted 0.05, 0.10, 0.15, 0.20, 0.25, 0.25 for L0 to L5, each level score a weighted mix of structural validity and distribution match, reference similarity and instruction-constraint satisfaction checked by code (no LLM judge; efficiency excluded), over the 800 instructions of GraphInstruct (instruction-following graph generation in six constraint levels); few-shot prompting with three same-level demonstrations; 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. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 88.4 | #173 |
| 2 | Qwen 3.5 122B A10B | 85.3 | #346 |
| 3 | GPT-4.1 | 85 | #505 |
| 4 | Qwen 3.5 397B A17B | 84.8 | #264 |
| 5 | GPT-4o | 84.4 | #751 |
| 6 | GraphInstruct DeepSeek-V3 (checkpoint unspecified) | 84 | |
| 7 | Llama 3.3 70B Instruct | 83.1 | #1385 |
| 8 | Qwen 3.5 35B A3B | 83.1 | #492 |
| 9 | GPT-4o Mini | 74.2 | #1667 |
| 10 | GPT-3.5 Turbo | 73.8 | #3005 |
| 11 | Llama 3.1 8B Instruct | 68.2 | #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-few-shot · How It Works · Data refreshed daily, snapshot 2026-11-21.