GSM8k
Grade School Math 8K, a dataset of 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.
Kimi K2 Instruct from Moonshot AI currently leads the GSM8k leaderboard with a score of 0.973 across 47 evaluated AI models.
Kimi K2 Instruct leads with 97.3%, followed by 
o1 at 97.1% and GPT-4.5 at 97.0%.
Progress Over Time
Interactive timeline showing model performance evolution on GSM8k
GSM8k Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Moonshot AI | 1.0T | — | — | ||
| 2 | OpenAI | — | — | — | ||
| 3 | OpenAI | — | — | — | ||
| 4 | 405B | — | — | |||
| 5 |  Anthropic | — | — | — | ||
| 5 | Anthropic | — | — | — | ||
| 7 |  Google | 27B | — | — | ||
| 7 |  Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 9 | Alibaba Cloud / Qwen Team | 73B | — | — | ||
| 10 |  DeepSeek | 236B | — | — | ||
| 11 | Anthropic | — | — | — | ||
| 12 | Alibaba Cloud / Qwen Team | 15B | — | — | ||
| 12 |  Amazon | — | — | — | ||
| 14 | Amazon | — | — | — | ||
| 15 | Google | 12B | — | — | ||
| 16 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 17 |  Mistral AI | 123B | — | — | ||
| 18 | Anthropic | — | — | — | ||
| 18 | Amazon | — | — | — | ||
| 20 | Moonshot AI | 1.0T | — | — | ||
| 21 | Alibaba Cloud / Qwen Team | 8B | — | — | ||
| 22 | 70B | — | — | |||
| 23 | Alibaba Cloud / Qwen Team | 72B | — | — | ||
| 23 | Alibaba Cloud / Qwen Team | 32B | — | — | ||
| 25 | Google | — | — | — | ||
| 26 |  xAI | — | — | — | ||
| 27 | Google | 4B | — | — | ||
| 28 | Anthropic | — | — | — | ||
| 29 |  Microsoft | 60B | — | — | ||
| 29 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 31 | Microsoft | 4B | — | — | ||
| 32 |  AI21 Labs | 398B | — | — | ||
| 33 | Microsoft | 4B | — | — | ||
| 33 | Google | — | — | — | ||
| 35 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 36 | Alibaba Cloud / Qwen Team | 8B | — | — | ||
| 37 | 8B | — | — | |||
| 38 | Mistral AI | 24B | — | — | ||
| 39 | 3B | — | — | |||
| 40 | AI21 Labs | 52B | — | — | ||
| 41 | Google | 27B | — | — | ||
| 42 |  Cohere | 104B | — | — | ||
| 43 | 7B | — | — | |||
| 44 | Google | 9B | — | — | ||
| 45 | Google | 1B | — | — | ||
| 46 | 8B | — | — | |||
| 47 |  Baidu | 21B | — | — |
FAQ
Common questions about GSM8k.
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