Qasper
QASPER is a dataset of 5,049 information-seeking questions and answers anchored in 1,585 NLP research papers. Questions are written by NLP practitioners who read only titles and abstracts, while answers require understanding the full paper text and provide supporting evidence. The dataset challenges models with complex reasoning across document sections for academic document question answering. Each question seeks information present in the full text and is answered by a separate set of NLP practitioners who also provide supporting evidence to answers.
Phi-3.5-mini-instruct from Microsoft currently leads the Qasper leaderboard with a score of 0.419 across 2 evaluated AI models.
Phi-3.5-mini-instruct leads with 41.9%, followed by Phi-3.5-MoE-instruct at 40.0%.
Progress Over Time
Interactive timeline showing model performance evolution on Qasper
Qasper Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Microsoft | 4B | — | — | ||
| 2 | Microsoft | 60B | — | — |
FAQ
Common questions about Qasper.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions