BioMedHop (Direct Prompting) - Path-based Reasoning: leaderboard
Metric: Accuracy (%; mean of multiple-choice accuracy and alias-normalised open-answer accuracy on Path-based Reasoning (the hidden disease on a typed five-node SPOKE metapath); stratified evaluation subsets of the 10,045 instances; direct input-output prompting with no retrieved evidence (the paper's IO baseline), temperature 0, at most 1,024 output tokens). Source: arxiv.org. Saturation forecast: Around 2032. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Turbo | 26.1 |
| 2 | Claude 3.7 Sonnet | 25.5 |
| 3 | Gemini 2.5 Pro | 25.4 |
| 4 | Qwen 3 Next 80B A3B Instruct | 23.5 |
| 5 | Claude 3.5 Haiku | 21.4 |
| 6 | GPT-4o Mini | 19.8 |
| 7 | MiMo-V2.5-Pro | 19.5 |
| 8 | Qwen 3 4B | 16 |
Interactive version: theaggregate.ai/benchmark?slug=biomedhop-direct-prompting-path-based-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-26.