LongBench v2
LongBench v2 is a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. It consists of 503 challenging multiple-choice questions with contexts ranging from 8k to 2M words across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding.
Qwen3.5-397B-A17B from Alibaba Cloud / Qwen Team currently leads the LongBench v2 leaderboard with a score of 0.632 across 14 evaluated AI models.
Qwen3.5-397B-A17B leads with 63.2%, followed by Qwen3.6 Plus at 62.0% and 
MiniMax M1 80K at 61.5%.
Progress Over Time
Interactive timeline showing model performance evolution on LongBench v2
LongBench v2 Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 397B | 262K | $0.60 / $3.60 | ||
| 2 | Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 3 |  MiniMax | 456B | — | — | ||
| 4 |  Moonshot AI | 1.0T | — | — | ||
| 4 | MiniMax | 456B | — | — | ||
| 6 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 6 |  Xiaomi | 309B | — | — | ||
| 8 | Alibaba Cloud / Qwen Team | 122B | 262K | $0.40 / $3.20 | ||
| 9 | Alibaba Cloud / Qwen Team | 35B | 262K | $0.25 / $2.00 | ||
| 10 | Alibaba Cloud / Qwen Team | 9B | — | — | ||
| 11 | Alibaba Cloud / Qwen Team | 4B | — | — | ||
| 12 |  DeepSeek | 671B | — | — | ||
| 13 | Alibaba Cloud / Qwen Team | 2B | — | — | ||
| 14 | Alibaba Cloud / Qwen Team | 800M | — | — |
FAQ
Common questions about LongBench v2.
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