Artificial Analysis
#26of 51
Score 24.1. Best run: openai/gpt-5.4-mini.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
OpenAI
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GPT-5.4 Mini, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#48of 85
on the LLM leaderboard, with a consensus score of 45 across 3 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Artificial Analysis
#26of 51
Score 24.1. Best run: openai/gpt-5.4-mini.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
LiveBench
#30of 34
Score 66.4. Best run: GPT 5.4 Mini xHigh.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#26of 79
Score 1449. Best run: gpt-5.4-mini-high.
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
$1.69
OpenRouter: $0.75 in, $4.50 out. Vercel AI Gateway: $0.75 in, $4.50 out Context window 400K tokens. LiveBench cost per solved task $0.334.
Nearby
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.