Compare AI models head to head
Pick a matchup to see, leaderboard by leaderboard, which side has the higher published score. We only list pairs that share at least 3 public benchmarks in our data, and every score links to its source.
Claude higher on 16 · ChatGPT higher on 4
20 shared leaderboards · Multi-domain agent tasks, Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preference, MultilingualSee the head-to-head →ChatGPT vs GeminiChatGPT higher on 9 · Gemini higher on 10 · 1 tied
20 shared leaderboards · Multi-domain agent tasks, Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preference, MultilingualSee the head-to-head →Claude vs GeminiClaude higher on 16 · Gemini higher on 4
20 shared leaderboards · Multi-domain agent tasks, Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preference, MultilingualSee the head-to-head →Grok vs ChatGPTGrok higher on 3 · ChatGPT higher on 13 · 2 tied
18 shared leaderboards · Multi-domain agent tasks, Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preferenceSee the head-to-head →Grok vs ClaudeGrok higher on 2 · Claude higher on 16
18 shared leaderboards · Multi-domain agent tasks, Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preferenceSee the head-to-head →Grok vs GeminiGrok higher on 3 · Gemini higher on 13 · 2 tied
18 shared leaderboards · Multi-domain agent tasks, Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preferenceSee the head-to-head →DeepSeek vs ChatGPTDeepSeek higher on 3 · ChatGPT higher on 11
14 shared leaderboards · Multi-domain agent tasks, Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preference, MultilingualSee the head-to-head →Qwen vs ChatGPTQwen higher on 2 · ChatGPT higher on 10 · 1 tied
13 shared leaderboards · Legal, Health & medical, Finance, Coding, Agents & tool use, Reasoning & knowledge, Chat preference, MultilingualSee the head-to-head →Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results
Questions people ask
How do you decide which comparisons to publish?
We only publish a comparison when both sides have a reported score on at least 3 of the same public leaderboards in our data. On each leaderboard we compare each side’s best-ranked model, using the score exactly as the source published it.
How often are these updated?
They are rebuilt from the same benchmark data as our leaderboards, which we check daily. Each comparison shows every leaderboard’s own date.
Is Claude better than ChatGPT?
On the 20 public leaderboards where both have a reported score, Claude’s best-ranked model scores higher on 16, ChatGPT’s on 4.
Is ChatGPT better than Gemini?
On the 20 public leaderboards where both have a reported score, ChatGPT’s best-ranked model scores higher on 9, Gemini’s on 10, and 1 is tied.
Is Claude better than Gemini?
On the 20 public leaderboards where both have a reported score, Claude’s best-ranked model scores higher on 16, Gemini’s on 4.
Is Grok better than ChatGPT?
On the 18 public leaderboards where both have a reported score, Grok’s best-ranked model scores higher on 3, ChatGPT’s on 13, and 2 are tied.