HellaSwag
Each model’s result as Epoch AI’s Benchmarking Hub publishes it, run by Epoch or collected from the source it cites. Facthory has not run them.
Data: Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks, licensed CC BY 4.0. Read on 16 Nov 2026.
The chart shows the 25 best of 76 results; the table lists them all.
| # | Model | Organization | Result | Evidence |
|---|---|---|---|---|
| 1 | GPT-4 (Mar 2023) API access | OpenAI | 95.3% | – |
| 2 | gpt-4-32k-0314 API access | OpenAI | 95.3% | – |
| 3 | Llama-3.1-405B Open weights (restricted use) | Meta AI | 89.2% | Log or source |
| 4 | falcon-180B Open weights (restricted use) | Technology Innovation Institute | 89% | – |
| 5 | DeepSeek-V3 Open weights (restricted use) | DeepSeek | 88.9% | Log or source |
| 6 | DeepSeek-V2 Open weights (restricted use) | DeepSeek | 87.1% | Log or source |
| 7 | PaLM 2-L | – | 86.8% | Log or source |
| 8 | Mixtral-8x7B-v0.1 Open weights (unrestricted) | Mistral AI | 86.7% | Log or source |
| 9 | text-davinci-003 | OpenAI | 85.5% | – |
| 10 | Llama-2-70b-hf Open weights (restricted use) | Meta AI | 85.3% | – |
| 11 | Qwen2.5-72B Open weights (unrestricted) | Alibaba | 84.8% | Log or source |
| 12 | LLaMA-65B Open weights (non-commercial) | Meta AI | 84.2% | Log or source |
| 13 | StableBeluga2 Open weights (non-commercial) | Stability AI | 84.1% | – |
| 14 | PaLM 2-M | – | 84% | Log or source |
| 15 | PaLM 540B Unreleased | Google Research | 83.4% | Log or source |
| 16 | Qwen2.5-Coder-32B Open weights (unrestricted) | Alibaba | 83% | Log or source |
| 17 | LLaMA-33B Open weights (non-commercial) | Meta AI | 82.8% | Log or source |
| 18 | falcon-40b Open weights (unrestricted) | Technology Innovation Institute | 82.8% | – |
| 19 | Megatron-Turing NLG 530B Unreleased | Microsoft,Nvidia | 82.4% | – |
| 20 | Nemotron-4 15B Unreleased | Nvidia | 82.4% | – |
| 21 | Phi-3-medium-128k-instruct Open weights (unrestricted) | Microsoft | 82.4% | – |
| 22 | gemma-7b Open weights (restricted use) | Google DeepMind | 82.2% | Log or source |
| 23 | Falcon 2-11B Open weights (restricted use) | Technology Innovation Institute | 82.1% | – |
| 24 | PaLM 2-S | – | 82% | Log or source |
| 25 | text-davinci-002 API access | OpenAI | 81.5% | Log or source |
| 26 | Mistral-7B-v0.1 Open weights (unrestricted) | Mistral AI | 81% | Log or source |
| 27 | Llama-2-13b Open weights (restricted use) | Meta AI | 80.7% | Log or source |
| 28 | Qwen2.5-Coder-14B | – | 80.2% | Log or source |
| 29 | Gopher (280B) Unreleased | DeepMind | 79.2% | Log or source |
| 30 | LLaMA-13B Open weights (non-commercial) | Meta AI | 79.2% | Log or source |
| 31 | opt-175b Open weights (non-commercial) | Meta AI | 79.1% | Log or source |
| 32 | text-davinci-001 API access | OpenAI | 78.9% | Log or source |
| 33 | internlm-20b | – | 78.1% | – |
| 34 | davinci API access | OpenAI | 77.5% | Log or source |
| 35 | Llama-2-7b Open weights (restricted use) | Meta AI | 77.2% | Log or source |
| 36 | Phi-3-small-8k-instruct Open weights (unrestricted) | Microsoft | 77% | – |
| 37 | Qwen2.5-Coder-7B Open weights (unrestricted) | Alibaba | 76.8% | Log or source |
| 38 | Phi-3-mini-4k-instruct Open weights (unrestricted) | Microsoft | 76.7% | – |
| 39 | GLaM (MoE) Unreleased | 76.6% | – | |
| 40 | Yi-9B | – | 76.4% | – |
| 41 | mpt-7b Open weights (unrestricted) | MosaicML | 76.4% | – |
| 42 | falcon-7b Open weights (unrestricted) | Technology Innovation Institute | 76.3% | – |
| 43 | LLaMA-7B Open weights (non-commercial) | Meta AI | 76.1% | Log or source |
| 44 | opt-66b Open weights (non-commercial) | Meta AI | 74.5% | Log or source |
| 45 | Yi-6B Open weights (restricted use) | 01.AI | 74.4% | – |
| 46 | bloom Open weights (restricted use) | Hugging Face,BigScience | 74.4% | Log or source |
| 47 | xgen-7b-8k-base Open weights (unrestricted) | Salesforce | 74.2% | – |
| 48 | open_llama_7b | – | 71.8% | – |
| 49 | INTELLECT-1-Instruct | Prime Intellect,Hugging Face,Arcee AI | 71.4% | Log or source |
| 50 | gemma-2b Open weights (restricted use) | Google DeepMind | 71.4% | Log or source |
| 51 | Qwen2.5-Coder-3B | – | 70.9% | Log or source |
| 52 | Baichuan-2-13B-Base Open weights (restricted use) | Baichuan | 70.8% | – |
| 53 | dolly-v2-12b Open weights (unrestricted) | Databricks | 70.8% | – |
| 54 | internlm-7b | – | 70.6% | – |
| 55 | gpt-neox-20b Open weights (unrestricted) | EleutherAI | 70.5% | – |
| 56 | RedPajama-INCITE-7B-Base | – | 70.3% | – |
| 57 | opt-13b | – | 69.9% | – |
| 58 | curie | OpenAI | 68.2% | Log or source |
| 59 | Baichuan-2-7B-Base Open weights (restricted use) | Baichuan | 68% | – |
| 60 | text-curie-001 API access | OpenAI | 67.6% | Log or source |
| 61 | gpt-j-6b Open weights (unrestricted) | EleutherAI,LAION | 66.2% | – |
| 62 | Qwen2.5-Coder-1.5B Open weights (unrestricted) | Alibaba | 61.8% | Log or source |
| 63 | Cerebras-GPT-13B Open weights (unrestricted) | Cerebras Systems | 59.4% | – |
| 64 | vicuna-13b-v1.1 | – | 57.8% | – |
| 65 | chatglm2-6b | – | 57% | – |
| 66 | text-babbage-001 API access | OpenAI | 56.1% | Log or source |
| 67 | babbage | OpenAI | 55.5% | Log or source |
| 68 | phi-2 Open weights (unrestricted) | Microsoft | 53.6% | – |
| 69 | Qwen2.5-Coder-0.5B | – | 48.4% | Log or source |
| 70 | phi-1_5 Open weights (unrestricted) | Microsoft | 47.6% | – |
| 71 | ada | OpenAI | 43.5% | Log or source |
| 72 | text-ada-001 | OpenAI | 42.9% | Log or source |
| 73 | gpt-neo-2.7B Open weights (unrestricted) | EleutherAI | 42.7% | – |
| 74 | opt-1.3b Open weights (non-commercial) | Meta AI | 41.5% | – |
| 75 | stablelm-tuned-alpha-7b | – | 40.7% | – |
| 76 | gpt2-xl Open weights (unrestricted) | OpenAI | 40% | – |
