LiveBench Language Leaderboard
Compare models on LiveBench Language benchmarks.
Rank | Model | Score | Organization | License |
---|---|---|---|---|
1 | o3OpenAI | 76.00 | OpenAI | Proprietary |
2 | o3OpenAI | 76.00 | OpenAI | Proprietary |
3 | Gemini 2.5 Pro PreviewGoogle | 71.81 | Proprietary | |
4 | o4-miniOpenAI | 66.05 | OpenAI | Proprietary |
5 | Claude 3.7 SonnetAnthropic | 63.19 | Anthropic | Proprietary |
6 | Gemini 2.5 Flash PreviewGoogle | 59.43 | Proprietary | |
7 | GPT-4.1OpenAI | 54.55 | OpenAI | Proprietary |
8 | Claude 3.5 SonnetAnthropic | 54.48 | Anthropic | Proprietary |
9 | ChatGPT-4oOpenAI | 49.43 | OpenAI | Proprietary |
10 | GPT-4 TurboOpenAI | 44.68 | OpenAI | Proprietary |
11 | GPT-4o 2024-05-13OpenAI | 44.68 | OpenAI | Proprietary |
12 | GPT-4oOpenAI | 44.68 | OpenAI | Proprietary |
13 | GPT-4oOpenAI | 44.68 | OpenAI | Proprietary |
14 | GPT-4oOpenAI | 44.68 | OpenAI | Proprietary |
15 | GPT-3.5 Turbo (0125)OpenAI | 44.68 | OpenAI | Proprietary |
16 | Gemini 2.0 FlashGoogle | 42.39 | Proprietary | |
17 | Gemini 2.0 FlashGoogle | 42.39 | Proprietary | |
18 | Claude 3.5 HaikuAnthropic | 39.71 | Anthropic | Proprietary |
19 | Claude 3 HaikuAnthropic | 39.71 | Anthropic | Proprietary |
20 | Claude 3 HaikuAnthropic | 39.71 | Anthropic | Proprietary |
21 | o1OpenAI | 38.41 | OpenAI | Proprietary |
22 | GPT-4.1 miniOpenAI | 38.00 | OpenAI | Proprietary |
23 | Gemini 2.0 Flash-LiteGoogle | 33.94 | Proprietary | |
24 | GPT-4.1 nanoOpenAI | 30.96 | OpenAI | Proprietary |
25 | GPT-4o miniOpenAI | 29.88 | OpenAI | Proprietary |