lmarena top 3
- User
lmarena top 3
Assistant
As of April 2025, the top three models on the LMArena leaderboard based on Arena Elo ratings are:
-
Gemini-2.5-Pro-Exp-03-25
- Arena Elo: 1440
- Key Strength: Leads in scientific reasoning with an 84% score on the GPQA Diamond benchmark[5].
-
ChatGPT-4o-latest (2025-03-26)
- Arena Elo: 1406
- Key Strength: Maintains strong performance in general-purpose tasks and coding[2].
-
Grok-3-Preview-02-24
- Arena Elo: 1404
- Key Strength: Excels in math benchmarks like AIME 2025 (93.3% with multiple attempts)[5].
These rankings reflect human preference evaluations from over 2.8 million user votes[2]. For specialized domains like web development, Claude 3.7 Sonnet leads with an Arena Score of 1351.69[3].
-
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- gpt-4o-mini-search-previewCompare side by side →
sonar-reasoningCompare side by side →
sonarCompare side by side →
- gpt-4o-search-previewCompare side by side →
sonar-reasoningCompare side by side →
- gpt-4o-search-preview-highCompare side by side →
sonar-pro-highCompare side by side →
- gpt-4o-search-preview-highCompare side by side →
sonarCompare side by side →
- gpt-4o-search-preview-high-locCompare side by side →
sonar-reasoningCompare side by side →
- gpt-4o-mini-search-previewCompare side by side →