PlantMarkerBench — leaderboard
Metric: Valid F1 (self-reported). Source: benchmarklist.com. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 32B Instruct | 75.4 |
| 2 | Mistral 7B Instruct | 69 |
| 3 | GPT-OSS-20B | 67.3 |
| 4 | Qwen 2.5 7B Instruct | 67.1 |
| 5 | Qwen 2.5 1.5B Instruct | 66.7 |
| 6 | Llama 3.2 1B | 66.7 |
| 7 | Llama 3.1 8B | 63.4 |
| 8 | GPT-5.4 Mini | 63.3 |
| 9 | GPT-5.4 | 54.9 |
| 10 | Qwen 2.5 14B Instruct | 51.4 |
| 11 | Llama 3.2 3B | 44.9 |
| 12 | Qwen 2.5 3B Instruct | 24.7 |
Interactive version: theaggregate.ai/benchmark?slug=plantmarkerbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.