| GPT-4o mini | 88.7% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| Phi-3.5-MoE | 88.6% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| Gemini 1.5 Flash | 87.5% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| Llama 3.1 405B | 85.9% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| Falcon-180B Chat | 84.9% | Self-reported | The Falcon Series of Open Language Models via Epoch AI | — |
| Inflection-1 | 84.2% | Third party | The Falcon Series of Open Language Models via Epoch AI | — |
| DeepSeek-V2 | 83.9% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| Gemma 2 9B | 83.7% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| Stable Beluga 2 (Llama 2 70B fine-tune) | 83.3% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Falcon-40B Instruct | 83.0% | Self-reported | The Falcon Series of Open Language Models via Epoch AI | — |
| Mistral 7B v0.1 | 83.0% | Self-reported | Nemotron-4 15B Technical Report via Epoch AI | — |
| Falcon-40B Instruct | 82.4% | Third party | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 82.3% | Third party | GLaM: Efficient Scaling of Language Models with Mixture-of-Experts via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 82.3% | Third party | Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model via Epoch AI | — |
| Mistral 7B v0.1 | 82.2% | Third party | Mixtral of Experts via Epoch AI | — |
| Mistral 7B v0.2 | 82.2% | Third party | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| MPT-30B (Instruct, Chat) | 81.9% | Third party | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| Gemma 7B | 81.2% | Self-reported | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Gemma 7B | 81.2% | Self-reported | Nemotron-4 15B Technical Report via Epoch AI | — |
| Llama 3.1 8B | 81.2% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| Phi-3.5-mini | 81.0% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 81.0% | Third party | Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 81.0% | Third party | LLaMA: Open and Efficient Foundation Language Models via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 81.0% | Third party | The Falcon Series of Open Language Models via Epoch AI | — |
| Llama 2 13B | 80.8% | Third party | Mixtral of Experts via Epoch AI | — |
| MPT-7B (Instruct, Chat, StoryWriter) | 80.6% | Self-reported | Qwen Technical Report via Epoch AI | — |
| MPT-7B (Instruct, Chat, StoryWriter) | 80.6% | Third party | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| Llama 2 13B | 80.5% | Third party | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Llama 2 13B | 80.5% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Llama 2 13B | 80.5% | Self-reported | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| Llama 2 13B | 80.5% | Third party | The Falcon Series of Open Language Models via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 80.5% | Third party | GLaM: Efficient Scaling of Language Models with Mixture-of-Experts via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 80.5% | Third party | Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model via Epoch AI | — |
| text-davinci-001 (InstructGPT) | 80.4% | Third party | GLaM: Efficient Scaling of Language Models with Mixture-of-Experts via Epoch AI | — |
| Falcon-7B Instruct | 80.3% | Self-reported | The Falcon Series of Open Language Models via Epoch AI | — |
| Llama 2 13B | 79.8% | Self-reported | Nemotron-4 15B Technical Report via Epoch AI | — |
| Falcon-7B Instruct | 79.4% | Self-reported | Textbooks Are All You Need II: phi-1.5 technical report via Epoch AI | — |
| Falcon-7B Instruct | 79.4% | Self-reported | XGen-7B Technical Report via Epoch AI | — |
| MPT-7B (Instruct, Chat, StoryWriter) | 79.1% | Self-reported | XGen-7B Technical Report via Epoch AI | — |
| MPT-7B (Instruct, Chat, StoryWriter) | 78.9% | Self-reported | Textbooks Are All You Need II: phi-1.5 technical report via Epoch AI | — |
| Llama 2 7B | 78.8% | Third party | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Llama 2 7B | 78.8% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Llama 2 7B | 78.8% | Self-reported | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| Llama 2 7B | 78.8% | Third party | The Falcon Series of Open Language Models via Epoch AI | — |
| Llama 2 7B | 78.1% | Self-reported | Textbooks Are All You Need II: phi-1.5 technical report via Epoch AI | — |
| Llama 2 7B | 77.9% | Third party | Mixtral of Experts via Epoch AI | — |
| Gemma 2B | 77.3% | Self-reported | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Falcon-7B Instruct | 76.7% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Falcon-7B Instruct | 76.7% | Third party | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| Baichuan-7B (base) | 76.2% | Self-reported | Qwen Technical Report via Epoch AI | — |
| OPT-13B | 75.7% | Self-reported | XGen-7B Technical Report via Epoch AI | — |
| Dolly 2.0 (3B, 7B, 12B) | 75.4% | Self-reported | XGen-7B Technical Report via Epoch AI | — |
| Mistral 7B v0.1 | 73.4% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| GPT-2 XL (1.5B) | 70.5% | Self-reported | Textbooks Are All You Need II: phi-1.5 technical report via Epoch AI | — |
| ChatGLM2-6B | 69.6% | Self-reported | Qwen Technical Report via Epoch AI | — |
| OPT-1.3B | 69.0% | Self-reported | Textbooks Are All You Need II: phi-1.5 technical report via Epoch AI | — |
| StableLM-Alpha 7B | 65.8% | Self-reported | XGen-7B Technical Report via Epoch AI | — |