SuperGPQA
SuperGPQA is a comprehensive benchmark that evaluates large language models across 285 graduate-level academic disciplines. The benchmark contains 25,957 questions covering 13 broad disciplinary areas including Engineering, Medicine, Science, and Law, with specialized fields in light industry, agriculture, and service-oriented domains. It employs a Human-LLM collaborative filtering mechanism with over 80 expert annotators to create challenging questions that assess graduate-level knowledge and reasoning capabilities.
Qwen3.7 Max from Alibaba Cloud / Qwen Team currently leads the SuperGPQA leaderboard with a score of 0.736 across 31 evaluated AI models.
What SuperGPQA measures
SuperGPQA is a text benchmark that evaluates large language models on legal, math, physics, reasoning, finance, general, healthcare, chemistry, and economics tasks. LLM Stats tracks 31 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.6, with the leader reaching 0.7.
Compare leaders on the best AI for legal, best AI for math, best AI for physics, best AI for reasoning, best AI for finance, best AI for general, best AI for healthcare, best AI for chemistry and best AI for economics leaderboards.
Publication
- Paper
- SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
- Authors
- M-A-P Team, Xinrun Du, Yifan Yao, Kaijing Ma, and 93 others
- Published
- arXiv
- 2502.14739
Abstract
Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e.g., the reasoning-focused model DeepSeek-R1 achieved the highest accuracy of 61.82% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.
Qwen3.7 Max leads with 73.6%, followed by Qwen3.6 Plus at 71.6% and Qwen3.5-397B-A17B at 70.4%.
Progress Over Time
Interactive timeline showing model performance evolution on SuperGPQA
SuperGPQA Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | — | 1.0M | $1.25 / $3.75 | ||
| 2 | Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 3 | Alibaba Cloud / Qwen Team | 397B | 262K | $0.60 / $3.60 | ||
| 4 | Alibaba Cloud / Qwen Team | 122B | 262K | $0.40 / $3.20 | ||
| 5 | Alibaba Cloud / Qwen Team | 28B | 262K | $0.60 / $3.60 | ||
| 6 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 7 | Alibaba Cloud / Qwen Team | 1.0T | — | — | ||
| 8 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 9 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 10 | Alibaba Cloud / Qwen Team | 236B | — | — | ||
| 11 | Alibaba Cloud / Qwen Team | 35B | 262K | $0.25 / $2.00 | ||
| 12 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 13 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 14 | Alibaba Cloud / Qwen Team | 236B | 262K | $0.30 / $1.50 | ||
| 15 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 16 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 17 | Alibaba Cloud / Qwen Team | 9B | — | — | ||
| 18 |  Moonshot AI | 1.0T | — | — | ||
| 18 | Moonshot AI | 1.0T | — | — | ||
| 20 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 21 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 22 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 23 | Alibaba Cloud / Qwen Team | 4B | — | — | ||
| 24 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.18 / $2.09 | ||
| 25 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $1.00 | ||
| 26 | Moonshot AI | 1.0T | — | — | ||
| 27 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.08 / $0.50 | ||
| 28 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 29 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $0.60 | ||
| 30 | Alibaba Cloud / Qwen Team | 2B | — | — | ||
| 31 | Alibaba Cloud / Qwen Team | 800M | — | — |
FAQ
Common questions about SuperGPQA.
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