Artificial Analysis
Not measured by Artificial Analysis.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
OpenAI
GPT 5.4 xHigh benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GPT 5.4 xHigh, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#9of 85
on the LLM leaderboard, with a consensus score of 73 across 2 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places GPT 5.4 xHigh
LiveBench
#7of 34
Score 78.0. Best run: GPT 5.4 xHigh.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#12of 79
Score 1478. Best run: gpt-5.4-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
$5.63
Vercel AI Gateway: $2.50 in, $15 out LiveBench cost per solved task $0.387.
Nearby
The models either side of GPT 5.4 xHigh
- #6gemini-3-pro79
- #7Claude Opus 4.879
- #8Claude Opus 4.7 xHigh Effort74
- #9GPT 5.4 xHigh73
- #10Gemini 3.1 Pro Preview72
- #11Muse Spark 1.172
- #12Grok 4.572
Questions about GPT 5.4 xHigh
How good is GPT 5.4 xHigh?
GPT 5.4 xHigh ranks #9 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 73 out of 100 across 2 leaderboards.
Is GPT 5.4 xHigh better than Claude Opus 4.7 xHigh Effort?
Not on the consensus: Claude Opus 4.7 xHigh Effort scores 74 to GPT 5.4 xHigh's 73. Compare them source by source below, since the leaderboards test different things.
Is GPT 5.4 xHigh better than Gemini 3.1 Pro Preview?
On the consensus, yes: 73 to 72.
How much does GPT 5.4 xHigh cost?
$2.50 per million input tokens and $15 per million output tokens on Vercel AI Gateway, the cheaper listing we read. Blended at three input tokens to one output, that is $5.63 per million.
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.