| Falcon-7B Instruct | 28.0% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Falcon-7B Instruct | 28.8% | Third party | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| MPT-7B (Instruct, Chat, StoryWriter) | 31.0% | Third party | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| Baichuan-7B (base) | 32.5% | Self-reported | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| Llama 2 7B | 32.6% | Third party | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Llama 2 7B | 32.6% | Self-reported | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| ChatGLM2-6B | 33.7% | Third party | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| ChatGLM2-6B | 33.7% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Gemma 2B | 35.2% | Self-reported | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| MPT-7B (Instruct, Chat, StoryWriter) | 35.2% | Third party | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| MPT-7B (Instruct, Chat, StoryWriter) | 35.6% | Self-reported | Qwen Technical Report via Epoch AI | — |
| InternLM-Chat-20B | 36.7% | Third party | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Falcon-40B Instruct | 37.1% | Self-reported | Qwen Technical Report via Epoch AI | — |
| MPT-30B (Instruct, Chat) | 38.0% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Baichuan2-13B-Chat | 38.8% | Third party | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Llama 2 7B | 39.2% | Third party | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| Llama 2 13B | 39.4% | Third party | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Llama 2 13B | 39.4% | Self-reported | Nemotron-4 15B Technical Report via Epoch AI | — |
| Llama 2 13B | 39.4% | Self-reported | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI | — |
| Mistral 7B v0.1 | 39.5% | Self-reported | Nemotron-4 15B Technical Report via Epoch AI | — |
| Yi-6B-Chat | 39.7% | Self-reported | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| InternLM-Chat-20B | 42.4% | Third party | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Llama 2 13B | 47.0% | Third party | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| Baichuan2-13B-Chat | 47.2% | Third party | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Yi-6B-Chat | 47.2% | Self-reported | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Qwen-14B-Chat | 49.7% | Third party | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Yi-34B-Chat | 51.4% | Self-reported | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Qwen-14B-Chat | 55.0% | Third party | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| Gemma 7B | 55.1% | Self-reported | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Gemma 7B | 55.1% | Self-reported | Nemotron-4 15B Technical Report via Epoch AI | — |
| Mistral 7B v0.1 | 56.1% | Third party | Gemma: Open Models Based on Gemini Research and Technology via Epoch AI | — |
| Phi-2 | 59.4% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| GPT-3.5 Turbo | 61.6% | Third party | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| Stable Beluga 2 (Llama 2 70B fine-tune) | 69.3% | Self-reported | Qwen Technical Report via Epoch AI | — |
| Yi-34B-Chat | 71.7% | Self-reported | Yi: Open Foundation Models by 01.AI via Epoch AI | — |
| GPT-4 | 75.1% | Third party | Baichuan 2: Open Large-scale Language Models via Epoch AI | — |
| DeepSeek-V2 | 78.8% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| DeepSeek-V2 | 78.8% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| Phi-3-medium | 81.4% | Self-reported | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI | — |
| DeepSeek-V3 | 82.9% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| Llama 3.1 405B | 82.9% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| Llama 3.1 405B | 82.9% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| DeepSeek-V3 | 87.5% | Self-reported | DeepSeek-V3 Technical Report via Epoch AI | — |
| Gemini 1.5 Pro | 89.2% | Third party | Gemini 1.5 report via Epoch AI | — |