ZebraLogic
ZebraLogic is an evaluation framework for assessing large language models' logical reasoning capabilities through logic grid puzzles derived from constraint satisfaction problems (CSPs). The benchmark consists of 1,000 programmatically generated puzzles with controllable and quantifiable complexity, revealing a 'curse of complexity' where model accuracy declines significantly as problem complexity grows.
Qwen3 VL 235B A22B Thinking from Alibaba Cloud / Qwen Team currently leads the ZebraLogic leaderboard with a score of 0.973 across 8 evaluated AI models.
Qwen3 VL 235B A22B Thinking leads with 97.3%, followed by 
LongCat-Flash-Thinking at 95.5% and Qwen3-235B-A22B-Instruct-2507 at 95.0%.
Progress Over Time
Interactive timeline showing model performance evolution on ZebraLogic
ZebraLogic Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 236B | 262K | $0.45 / $3.49 | ||
| 2 | Meituan | 560B | — | — | ||
| 3 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 4 | Meituan | 560B | 128K | $0.30 / $1.20 | ||
| 5 |  Moonshot AI | 1.0T | — | — | ||
| 5 | Moonshot AI | 1.0T | — | — | ||
| 7 |  MiniMax | 456B | — | — | ||
| 8 | MiniMax | 456B | — | — |
FAQ
Common questions about ZebraLogic.
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