SciImpact - Medicine: leaderboard

SciImpact impact-prediction pairs from medicine, across the impact dimensions; the model sees two artifacts from the same field and picks the one with higher impact; pairwise accuracy in percent, chance 50, higher is better.

Metric: Pairwise prediction accuracy (%, times 100) on medicine pairs, over SciImpact contrastive pairs (215,928 pairs over 19 fields, built from citation counts, best paper awards and Nobel prizes, patent citations, media attention, GitHub stars and Hugging Face downloads with impact thresholds): the model sees two same-field artifacts (title and abstract, README, dataset card or model card, truncated to 1,000 words) and names the one with higher future impact in a two-option forced choice parsed by exact match; the order is balanced so chance is 50%; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Haiku 4.573#583
2O4 Mini71#368
3GPT-4.1 Mini67.3#789
4Qwen 3 4B60.7#2348
5Qwen 2.5 14B59.7#1811
6Qwen 2.5 7B57.9#2929
7Ministral 3 3B57.7#3504
8Llama 3 8B55.6#5900
9Llama 3.1 8B55.2#5196
10nemotron-3-nano-30B-a3B53.3#1946
11Llama 3.2 3B52.5#7877

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=sciimpact-medicine · How It Works · Data refreshed daily, snapshot 2026-11-21.