SciImpact - Computer Science: leaderboard

SciImpact impact-prediction pairs from computer science, 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 computer science 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 2029. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1O4 Mini63.9#372
2Claude Haiku 4.563.1#587
3GPT-4.1 Mini62.5#799
4Qwen 2.5 14B59.7#1819
5Qwen 3 4B59#2379
6Qwen 2.5 7B58.7#2902
7Llama 3 8B56.1#5897
8Llama 3.1 8B56#5193
9Ministral 3 3B54.7#3606
10nemotron-3-nano-30B-a3B54.4#1902
11Llama 3.2 3B53.3#7835

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=sciimpact-computer-science · How It Works · Data refreshed daily, snapshot 2026-11-22.