Artificial Analysis
#104of 115
Score 6.7. Best run: openai/gpt-4.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
OpenAI
GPT-4 benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GPT-4, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 5, 2026
#116of 126
on the LLM leaderboard, with a consensus score of 23 across 2 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places GPT-4
LiveBench
Not measured by LiveBench.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#103of 115
Score 1313. Best run: gpt-4-0125-preview.
Blind head-to-head human votes, style controlled.
Berkeley BFCL
Not measured by Berkeley BFCL.
Function calling and tool use, single turn to multi turn and web search.
Price and context
$38
OpenRouter: $30 in, $60 out Context window 8K tokens.
Nearby
The models either side of GPT-4
- #113GPT-4o-mini24
- #114amazon-nova-pro-v1.024
- #115granite-3.1-8b-instruct23
- #116GPT-423
- #117Llama 3.1 70B Instruct22
- #118Mistral Small 322
- #119amazon-nova-micro-v1.022
Questions about GPT-4
How good is GPT-4?
GPT-4 ranks #116 of 126 models on the Rank.ai LLM leaderboard, with a consensus score of 23 out of 100 across 2 leaderboards.
Is GPT-4 better than granite-3.1-8b-instruct?
Not on the consensus: granite-3.1-8b-instruct scores 23 to GPT-4's 23. Compare them source by source below, since the leaderboards test different things.
Is GPT-4 better than Llama 3.1 70B Instruct?
On the consensus, yes: 23 to 22.
How much does GPT-4 cost?
$30 per million input tokens and $60 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $38 per million.
Is GPT-4 good for coding?
It scores 13.1 on the Artificial Analysis Coding Index, placing it #59 for coding among the models on this leaderboard.
These models recommend brands. See if they name yours.
Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.
- Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
- Who gets namedEvery competitor in the answers, most named first.
- The pages AI readsThe sources behind each answer.
- Three fixesWhat to fix first, with a brief for the first article.