GPT-4-0613, Large Language Model ELO
Crowdsourced ranking of LLMs according to human preferences
Latest news articles
Showing data for a single variable. See main chart
GPT-4-Turbo-2024-04-09 | 1257 |
GPT-4-1106-preview | 1253 |
Claude 3 Opus | 1251 |
Gemini 1.5 Pro API-0409-Preview | 1248 |
GPT-4-0125-preview | 1247 |
Bard (Gemini Pro) | 1209 |
Llama-3-70b-Instruct | 1207 |
Claude 3 Sonnet | 1202 |
Command R+ | 1192 |
GPT-4-0314 | 1189 |
Claude 3 Haiku | 1181 |
GPT-4-0613 | 1165 |
Mistral-Large-2402 | 1158 |
Qwen1.5-72B-Chat | 1153 |
Reka-Flash-21B-online | 1151 |
Claude-1 | 1150 |
Command R | 1148 |
Mistral Medium | 1148 |
Qwen1.5-32B-Chat | 1136 |
Gemini Pro (Dev API) | 1135 |
Claude-2.0 | 1127 |
Starling-LM-7B-beta | 1127 |
Mistral-Next | 1123 |
Claude-2.1 | 1115 |
Mixtral-8x7b-Instruct-v0.1 | 1114 |
89.53% | – D | – W | - 1.7 M | - 2 Y | |
21.0M | + 0% D | + 0.1% W | + 0.4% M | – Y |
About Realtime
Our system continuously tracks and analyzes key changes within public data on a range of topics: economics, politics, sports, and others. It then uses AI to generate live updating visualizations and reports.
To learn more about us, see our frequently asked questions or read about our motivation for starting Realtime.
Join the community
Realtime is currently in Beta, and we want to hear your input.
Join us on Discord to be the first to know about new data and features. There you can request additions to the platform and join discussions about the most impactful movements in data.