OpenAI

GPT-5.4 Nano benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GPT-5.4 Nano, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Oct 1, 2026Full leaderboard Sources and method

Read Oct 1, 2026

#62of 85

on the LLM leaderboard, with a consensus score of 38 across 3 leaderboards.

Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.

By leaderboard

Where each leaderboard places GPT-5.4 Nano

Artificial Analysis

#30of 51

Score 20.7. Best run: openai/gpt-5.4-nano.

Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.

LiveBench

#26of 34

Score 69.6. Best run: GPT 5.4 Nano xHigh.

Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.

LMArena

#51of 79

Score 1404. Best run: gpt-5.4-nano-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

$0.46

OpenRouter: $0.20 in, $1.25 out. Vercel AI Gateway: $0.20 in, $1.25 out Context window 400K tokens. LiveBench cost per solved task $0.091.

Nearby

The models either side of GPT-5.4 Nano

Questions about GPT-5.4 Nano

How good is GPT-5.4 Nano?

GPT-5.4 Nano ranks #62 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 38 out of 100 across 3 leaderboards.

Is GPT-5.4 Nano better than R1?

Not on the consensus: R1 scores 38 to GPT-5.4 Nano's 38. Compare them source by source below, since the leaderboards test different things.

Is GPT-5.4 Nano better than Qwen3 235B A22B Thinking 2507?

On the consensus, yes: 38 to 35.

How much does GPT-5.4 Nano cost?

$0.20 per million input tokens and $1.25 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $0.46 per million.

Is GPT-5.4 Nano good for coding?

It scores 56.1 on the Artificial Analysis Coding Index, placing it #23 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.