SciR - Induction Easy (Obfuscated): leaderboard

Metric: Accuracy (%) on the 200 easy-tier SciR induction tasks (rule induction over DrugBank drug-drug interaction facts), rendered as obfuscated multi-document scientific discourse (Obf: lab notes, drug labels, records and tables); the model reasons with chain-of-thought directly from the task text, temperature 0; answers are checked against the generating formal object; higher is better. Source: arxiv.org. Saturation forecast: Around September 2028. 6 models tracked.

Top models

#ModelScore
1GPT-4o36.5
2DeepSeek R136
3Olmo 3.1 32B Instruct32
4Qwen 3 30B A3B 2507 Instruct25.5
5Llama 3.3 70B Instruct23

Interactive version: theaggregate.ai/benchmark?slug=scir-induction-easy-obfuscated · How It Works · Data refreshed daily, snapshot 2026-09-29.