PlantMarkerBench: leaderboard
Cell-type-specific marker genes are fundamental to plant biology, yet existing resources primarily rely on curated databases or high-throughput studies without explicitly modeling the supporting evidence found in scientific literature. We introduce PlantMarkerBench, a multi-species benchmark for evaluating literature-grounded plant marker evidence interpretation from full-text biological papers. P
Metric: Valid F1 (self-reported). Source: benchmarklist.com. 51 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 32B Instruct | 0.75 | #498 |
| 2 | Mistral 7B Instruct | 0.69 | #1363 |
| 3 | Qwen 2.5 7B Instruct | 0.67 | #862 |
| 4 | GPT-OSS-20B | 0.67 | #518 |
| 5 | Llama 3.1 8B | 0.63 | #1151 |
| 6 | GPT-5.4 Mini | 0.63 | #212 |
| 7 | Qwen 2.5 14B Instruct | 0.51 | #647 |
| 8 | Llama 3.2 3B | 0.45 | #1396 |
| 9 | Qwen 2.5 3B Instruct | 0.25 | #1162 |
Interactive version: theaggregate.ai/benchmark?slug=plantmarkerbench · How It Works · Data refreshed daily, snapshot 2026-10-20.