Logo

LiveBench IF Leaderboard

Compare models on LiveBench IF benchmarks.

Last updated: May 22, 2025
RankModelScoreOrganizationLicenseUpdated At
1o3-2025-04-16OpenAI86.17OpenAIProprietaryMay 22, 2025
2o3OpenAI86.17OpenAIProprietaryMay 22, 2025
3google-gemini-2.0-flashGoogle85.79GoogleProprietaryMay 18, 2025
4google-gemini-2.0-flash-liveGoogle85.79GoogleProprietaryMay 18, 2025
5o4-miniOpenAI84.96OpenAIProprietaryMay 22, 2025
6google-gemini-2.5-pro-previewGoogle83.50GoogleProprietaryMay 18, 2025
7claude-opus-4-20250514Anthropic80.74AnthropicProprietaryMay 22, 2025
8google-gemini-2.5-flash-previewGoogle79.02GoogleProprietaryMay 18, 2025
9claude-opus-4-0Anthropic78.38AnthropicProprietaryMay 22, 2025
10claude-sonnet-4-20250514Anthropic77.25AnthropicProprietaryMay 22, 2025
11claude-sonnet-4-0Anthropic77.25AnthropicProprietaryMay 22, 2025
12gpt-4.1OpenAI77.05OpenAIProprietaryMay 22, 2025
13google-gemini-2.0-flash-liteGoogle76.63GoogleProprietaryMay 18, 2025
14claude-3-7-sonnet-20250219Anthropic76.49AnthropicProprietaryMay 22, 2025
15claude-3-7-sonnet-latestAnthropic76.49AnthropicProprietaryMay 22, 2025
16anthropic-claude-3-7-sonnetAnthropic76.49AnthropicProprietaryMay 22, 2025
17chatgpt-4oOpenAI71.92OpenAIProprietaryMay 22, 2025
18gpt-4oOpenAI71.92OpenAIProprietaryMay 22, 2025
19gpt-4.1-miniOpenAI70.31OpenAIProprietaryMay 22, 2025
20anthropic-claude-3-5-sonnetAnthropic69.30AnthropicProprietaryMay 22, 2025
21claude-3-5-sonnet-20241022Anthropic69.30AnthropicProprietaryMay 22, 2025
22claude-3-5-sonnet-20240620Anthropic69.30AnthropicProprietaryMay 22, 2025
23claude-3-5-sonnet-latestAnthropic69.30AnthropicProprietaryMay 22, 2025
24gpt-4o-2024-05-13OpenAI64.94OpenAIProprietaryMay 22, 2025
25gpt-4o-2024-11-20OpenAI64.94OpenAIProprietaryMay 22, 2025
26gpt-4o-2024-08-06OpenAI64.94OpenAIProprietaryMay 22, 2025
27claude-3-5-haiku-20241022Anthropic61.88AnthropicProprietaryMay 22, 2025
28anthropic-claude-3-5-haikuAnthropic61.88AnthropicProprietaryMay 22, 2025
29claude-3-5-haiku-latestAnthropic61.88AnthropicProprietaryMay 22, 2025
30gpt-4.1-nanoOpenAI57.54OpenAIProprietaryMay 22, 2025
31gpt-4o-miniOpenAI56.80OpenAIProprietaryMay 22, 2025