MHGraphBench — leaderboard
Metric: Avg$_{All^\ast}$ (self-reported). Source: benchmarklist.com. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 70.28 |
| 2 | GPT-5.2 | 69.32 |
| 3 | GPT-4o | 69.1 |
| 4 | GPT-5 Mini | 68.38 |
| 5 | GPT-5.1 | 68.33 |
| 6 | Qwen 2.5 32B | 56.09 |
| 7 | Qwen 2.5 7B | 43.61 |
| 8 | Mistral 7B | 42.1 |
| 9 | Llama 3.1 8B | 32.54 |
Interactive version: theaggregate.ai/benchmark?slug=mhgraphbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.