Chatbot Arena
Crowdsourced pairwise preference Elo.
Leaderboard
| # | Model | Provider | elo | Evaluated | Source |
|---|---|---|---|---|---|
| 1 | Gemini 2.0 Flash | Google DeepMind | 1356 | — | |
| 2 | GPT-4o | OpenAI | 1287 | — | |
| 3 | Claude 3.5 Sonnet | Anthropic | 1271 | — |
Crowdsourced pairwise preference Elo.
| # | Model | Provider | elo | Evaluated | Source |
|---|---|---|---|---|---|
| 1 | Gemini 2.0 Flash | Google DeepMind | 1356 | — | |
| 2 | GPT-4o | OpenAI | 1287 | — | |
| 3 | Claude 3.5 Sonnet | Anthropic | 1271 | — |