Noometry

Reasoning benchmark

HellaSwag leaderboard

As of October 2026, GPT-4 has the highest published HellaSwag score on Noometry at 95.3%, out of 29 models with results.

Last verified

About HellaSwag

Commonsense sentence completion with adversarially filtered wrong endings.

Category
Reasoning
Introduced
2019
Format
Multiple choice
Unit
Percent (random guessing ≈ 25%)
Official site
rowanzellers.com

Top 15 models

  1. GPT-4 95.3%
  2. GPT-4 95.3%
  3. Llama 3.1-405B 89.2%
  4. Falcon-180B 89%
  5. DeepSeek-V3 88.9%
  6. DeepSeek-V2 (MoE-236B, May 2024) 87.1%
  7. Mixtral 8x7B 86.7%
  8. Llama 2-70B 85.3%
  9. Falcon-40B 85.3%
  10. Qwen2.5 72B Instruct 84.8%
  11. Qwen2.5-Coder-32B 83%
  12. Falcon 2 11B 82.9%
  13. Nemotron-4 15B 82.4%
  14. phi-3-medium 14B 82.4%
  15. Gemma 7B 82.2%

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

All results

#ModelProviderScoreSettingSourceDate
1GPT-4 OpenAI95.3%Epoch AI
2GPT-4 OpenAI95.3%Epoch AI
3Llama 3.1-405B Meta89.2%Epoch AI
4Falcon-180B Technology Innovation Institute89%Epoch AI
5DeepSeek-V3 DeepSeek88.9%Epoch AI
6DeepSeek-V2 (MoE-236B, May 2024) DeepSeek87.1%Epoch AI
7Mixtral 8x7B Mistral AI86.7%Epoch AI
8Llama 2-70B Meta85.3%Epoch AI
9Falcon-40B Technology Innovation Institute85.3%Epoch AI
10Qwen2.5 72B Instruct Alibaba (Qwen)84.8%Epoch AI
11Qwen2.5-Coder-32B Alibaba (Qwen)83%Epoch AI
12Falcon 2 11B Technology Innovation Institute82.9%Epoch AI
13Nemotron-4 15B NVIDIA82.4%Epoch AI
14phi-3-medium 14B Microsoft82.4%Epoch AI
15Gemma 7B Google82.2%Epoch AI
16Mistral 7B Mistral AI81%Epoch AI
17Llama 2-13B Meta80.7%Epoch AI
18Llama 13b Meta79.2%Epoch AI
19Falcon-7B Technology Innovation Institute78.1%Epoch AI
20Llama 2-7B Meta77.2%Epoch AI
21Phi 3 Small 8k Instruct Microsoft77%Epoch AI
22Qwen2.5-Coder (1.5B) Alibaba (Qwen)76.8%Epoch AI
23Phi 3 Mini 4k Instruct Microsoft76.7%Epoch AI
24Yi 6B 01.AI74.4%Epoch AI
25INTELLECT-1 Hugging Face71.4%Epoch AI
26Gemma 2B Google71.4%Epoch AI
27Dolly 2.0-12b Databricks70.8%Epoch AI
28Phi-2 Microsoft53.6%Epoch AI
29Phi-1.5 Microsoft47.6%5Epoch AI

Compare the leaders

Other reasoning benchmarks

Frequently asked questions

What does HellaSwag measure?

Commonsense sentence completion with adversarially filtered wrong endings.

Which model has the highest HellaSwag score?

As of October 2026, GPT-4 has the highest published HellaSwag score on Noometry at 95.3%, out of 29 models with results.

What is the best open-weight model on HellaSwag?

Llama 3.1-405B has the highest HellaSwag accuracy among open-weight models at 89.2%, ranking 3 of 29 overall.