BioMedHop (Direct Prompting): leaderboard
Metric: Overall accuracy (%; mean of the four task-family scores, which are MCQ/open-answer accuracy averages and exact-count accuracy; 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 | Gemini 2.5 Pro | 18.6 |
| 2 | GPT-4 Turbo | 18.2 |
| 3 | Claude 3.7 Sonnet | 17.8 |
| 4 | Qwen 3 Next 80B A3B Instruct | 16.1 |
| 5 | Claude 3.5 Haiku | 14.5 |
| 6 | MiMo-V2.5-Pro | 13.7 |
| 7 | GPT-4o Mini | 13.2 |
| 8 | Qwen 3 4B | 9.3 |
Interactive version: theaggregate.ai/benchmark?slug=biomedhop-direct-prompting · How It Works · Data refreshed daily, snapshot 2026-09-26.