| model,latency | |
| Phi-3-mini-128k-instruct,0.6615315832127351 | |
| Meta-Llama-3.1-70B-Instruct,0.8105055275945272 | |
| Meta-Llama-3.1-405B-Instruct-Turbo,0.7886103946545832 | |
| mistral-medium-2312,3.3167870515212137 | |
| gemma-2-2b-it,0.3139821517919896 | |
| Meta-Llama-3-8B-Instruct-hf,2.116447543256806 | |
| Qwen1.5-1.8B-Chat,0.5502705450000004 | |
| CodeLlama-34b-Instruct-hf,3.851887315425931 | |
| Qwen2-72B-Instruct,0.9480584860151365 | |
| Meta-Llama-3.1-8B-Instruct,0.20630574840608434 | |
| gemma-1.1-7b-it,0.1782953878345513 | |
| gemma-2-27b-it,0.9922771009345804 | |
| openchat-3.5-1210,0.28049827691029705 | |
| codegemma-7b-it,0.30489740508652785 | |
| dolphin-2.5-mixtral-8x7b,1.100729847312237 | |
| sheep-duck-llama-2-70b-v1.1,5.524607914346896 | |
| gpt-4-0613,0.6484411465828742 | |
| Meta-Llama-3-70B-Instruct-hf,3.348256158662245 | |
| openchat_3.5,0.31728768684620623 | |
| Yi-34B-Chat,1.2871676207135385 | |
| gpt-4o-2024-05-13,0.5570990732389735 | |
| openchat-3.5-0106,0.2920951450556654 | |
| Mixtral-8x7B-Instruct-v0.1,0.9392967660636317 | |
| gpt-4,0.9930876319528372 | |
| Qwen1.5-14B-Chat,0.37289333481152975 | |
| mistral-large-2402,0.3967416598893948 | |
| claude-3-5-sonnet-20240620,0.879929281888541 | |
| gemma-7b-it,0.6112263564356414 | |
| gpt-4-0125-preview,1.0418927523113601 | |
| gpt-4-1106-preview,0.7767265743542753 | |
| gemini-1.5-pro-latest,82.90283880578006 | |
| Nous-Hermes-2-Mixtral-8x7B-SFT,0.860892263303385 | |
| claude-2.1,1.6836316221022491 | |
| gemma-1.1-2b-it,0.11925699461279458 | |
| claude-3-opus-20240229,2.955845827917778 | |
| command-r,0.18832414914586068 | |
| gpt-4o-mini-2024-07-18,0.5342684150088973 | |
| sheep-duck-llama-2-13b,2.9462099794520453 | |
| SUS-Chat-34B,2.27951476106911 | |
| claude-3-haiku-20240307,0.869549739619107 | |
| gpt-4o-2024-08-06,0.5169587531894035 | |
| Yi-1.5-34B-Chat,9.232551962889337 | |
| Qwen2-7B-Instruct,0.3589407217948713 | |
| Mixtral-8x22B-Instruct-v0.1,1.0759354563573875 | |
| vicuna-13b-v1.5,1.4753938719676492 | |
| gemma-2-9b-it,0.3692553324432539 | |
| Mistral-7B-Instruct-v0.2,0.7635151196709047 | |
| Qwen1.5-32B-Chat,0.5092292557397938 | |
| Qwen1.5-0.5B-Chat,0.173469139375476 | |
| Starling-LM-7B-beta,1.365002297029707 | |
| gemini-1.0-pro,0.6346876567117742 | |
| gemini-1.5-flash-latest,37.2042672100488 | |
| aya-23-35B,0.5755088395104249 | |
| llama-2-70b-chat-hf,4.724659620079609 | |
| Yi-1.5-9B-Chat,8.02352422018858 | |
| WizardLM-70b-v1.0,3.9249772038834863 | |
| Yi-1.5-6B-Chat,6.496741103848931 | |
| tulu-2-dpo-70b,7.848597339328551 | |
| Qwen1.5-72B-Chat,12.689668927658234 | |
| Mistral-7B-Instruct-v0.1,0.2828647550771723 | |
| gpt-3.5,0.6829601016193744 | |
| aya-23-8B,0.4818848185613409 | |
| Qwen1.5-7B-Chat,0.38989076908838965 | |
| claude-3-sonnet-20240229,1.419486012822594 | |
| vicuna-33b-v1.3,0.8235025152162343 | |
| WizardLM-13b-v1.2,3.565436762576296 | |
| Mistral-Large-Instruct-2407,1.2444667688634197 | |
| command-r-plus,0.3104016019283745 | |