Noometry

Math benchmark

GSM8K leaderboard

As of October 2026, Deepseek Coder v2 has the highest published GSM8K score on Noometry at 94.5%, out of 38 models with results.

Last verified

About GSM8K

Grade-school math word problems that need a few steps of arithmetic.

Category
Math
Introduced
2021
Size
8,500 problems
Format
Exact answer
Unit
Percent (random guessing ≈ 0%)
Official site
arxiv.org

Top 15 models

  1. Deepseek Coder v2 94.5%
  2. Qwen2.5-Coder-32B 93%
  3. GPT-4 92%
  4. GPT-4o mini 91.3%
  5. Phi-3.5-MoE 88.7%
  6. Claude Instant 86.7%
  7. Qwen2.5-Coder (1.5B) 86.7%
  8. Phi-3.5-mini 86.2%
  9. Gemma 2 9B 84.9%
  10. Mistral Nemo 84.2%
  11. Gemini 1.5 Flash (May 2024) 82.4%
  12. Llama 3.1-8B 82.4%
  13. Yi-34B 76%
  14. Mixtral 8x7B 74.4%
  15. Llama 2-70B 69.6%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1Deepseek Coder v2 DeepSeek94.5%Epoch AI
2Qwen2.5-Coder-32B Alibaba (Qwen)93%Epoch AI
3GPT-4 OpenAI92%Epoch AI
4GPT-4o mini OpenAI91.3%Epoch AI
5Phi-3.5-MoE Microsoft88.7%Epoch AI
6Claude Instant Anthropic86.7%Epoch AI
7Qwen2.5-Coder (1.5B) Alibaba (Qwen)86.7%Epoch AI
8Phi-3.5-mini Microsoft86.2%Epoch AI
9Gemma 2 9B Google84.9%Epoch AI
10Mistral Nemo Mistral AI84.2%Epoch AI
11Gemini 1.5 Flash (May 2024) Google82.4%Epoch AI
12Llama 3.1-8B Meta82.4%Epoch AI
13Yi-34B 01.AI76%Epoch AI
14Mixtral 8x7B Mistral AI74.4%Epoch AI
15Llama 2-70B Meta69.6%Epoch AI
16Qwen-14B Alibaba (Qwen)61.3%Epoch AI
17GPT-3.5-turbo OpenAI57.8%Epoch AI
18StarCoder 2 15B NVIDIA57.7%Epoch AI
19Falcon-180B Technology Innovation Institute54.4%Epoch AI
20Mistral 7B Mistral AI54.4%Epoch AI
21Falcon 2 11B Technology Innovation Institute53.8%Epoch AI
22Qwen-7B Alibaba (Qwen)51.7%Epoch AI
23Gemma 7B Google46.4%Epoch AI
24Nemotron-4 15B NVIDIA46%Epoch AI
25Yi 6B 01.AI44.9%Epoch AI
26Llama 2-34B Meta42.2%Epoch AI
27INTELLECT-1 Hugging Face38.6%Epoch AI
28Llama 2-13B Meta36.9%Epoch AI
29DeepSeek Coder 33B DeepSeek35.4%Epoch AI
30Falcon-40B Technology Innovation Institute33.8%Epoch AI
31StarCoder 2 7B NVIDIA32.7%Epoch AI
32StarCoder 2 3B NVIDIA21.6%Epoch AI
33DeepSeek Coder 6.7B DeepSeek21.3%Epoch AI
34Llama 13b Meta20.6%Epoch AI
35Gemma 2B Google17.7%Epoch AI
36Llama 2-7B Meta16.7%Epoch AI
37Falcon-7B Technology Innovation Institute6.8%Epoch AI
38DeepSeek Coder 1.3B DeepSeek4.4%Epoch AI

Compare the leaders

Other math benchmarks

Frequently asked questions

What does GSM8K measure?

Grade-school math word problems that need a few steps of arithmetic.

Which model has the highest GSM8K score?

As of October 2026, Deepseek Coder v2 has the highest published GSM8K score on Noometry at 94.5%, out of 38 models with results.

What is the best open-weight model on GSM8K?

Deepseek Coder v2 has the highest GSM8K accuracy among open-weight models at 94.5%, ranking 1 of 38 overall.