PlantMarkerBench: leaderboard
Metric: Valid F1 (self-reported). Source: benchmarklist.com. 51 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 32B Instruct | 0.75 |
| 2 | Mistral 7B Instruct | 0.69 |
| 3 | Qwen 2.5 1.5B Instruct | 0.67 |
| 4 | GPT-OSS-20B | 0.67 |
| 5 | Llama 3.2 1B | 0.67 |
| 6 | Qwen 2.5 7B Instruct | 0.67 |
| 7 | Qwen 2.5 0.5B | 0.67 |
| 8 | Llama 3.1 8B | 0.63 |
| 9 | GPT-5.4 Mini | 0.63 |
| 10 | GPT-5.4 | 0.55 |
| 11 | Qwen 2.5 14B Instruct | 0.51 |
| 12 | Llama 3.2 3B | 0.45 |
| 13 | Qwen 2.5 3B Instruct | 0.25 |
Interactive version: theaggregate.ai/benchmark?slug=plantmarkerbench · How It Works · Data refreshed daily, snapshot 2026-09-05.