LiveBench Reasoning Leaderboard
Compare models on LiveBench Reasoning benchmarks.
Rank | Model | Score | Organization | License |
---|---|---|---|---|
1 | o3OpenAI | 93.33 | OpenAI | Proprietary |
2 | o3OpenAI | 93.33 | OpenAI | Proprietary |
3 | Gemini 2.5 Pro PreviewGoogle | 88.25 | Proprietary | |
4 | o4-miniOpenAI | 88.11 | OpenAI | Proprietary |
5 | Gemini 2.5 Flash PreviewGoogle | 73.47 | Proprietary | |
6 | GPT-4.1 miniOpenAI | 53.78 | OpenAI | Proprietary |
7 | Claude 3.7 SonnetAnthropic | 49.11 | Anthropic | Proprietary |
8 | ChatGPT-4oOpenAI | 48.81 | OpenAI | Proprietary |
9 | GPT-4.1OpenAI | 44.39 | OpenAI | Proprietary |
10 | Gemini 2.0 FlashGoogle | 44.25 | Proprietary | |
11 | Gemini 2.0 FlashGoogle | 44.25 | Proprietary | |
12 | Claude 3.5 SonnetAnthropic | 43.22 | Anthropic | Proprietary |
13 | o1OpenAI | 42.39 | OpenAI | Proprietary |
14 | GPT-4 TurboOpenAI | 39.75 | OpenAI | Proprietary |
15 | GPT-4o 2024-05-13OpenAI | 39.75 | OpenAI | Proprietary |
16 | GPT-4oOpenAI | 39.75 | OpenAI | Proprietary |
17 | GPT-4oOpenAI | 39.75 | OpenAI | Proprietary |
18 | GPT-4oOpenAI | 39.75 | OpenAI | Proprietary |
19 | GPT-3.5 Turbo (0125)OpenAI | 39.75 | OpenAI | Proprietary |
20 | GPT-4.1 nanoOpenAI | 35.58 | OpenAI | Proprietary |
21 | Gemini 2.0 Flash-LiteGoogle | 32.25 | Proprietary | |
22 | Claude 3.5 HaikuAnthropic | 26.19 | Anthropic | Proprietary |
23 | Claude 3 HaikuAnthropic | 26.19 | Anthropic | Proprietary |
24 | Claude 3 HaikuAnthropic | 26.19 | Anthropic | Proprietary |
25 | GPT-4o miniOpenAI | 25.64 | OpenAI | Proprietary |