GPT-5.4: benchmarks, price and rank
GPT-5.4 from OpenAI is 46th of 123 rated AI models on Spezia's leaderboard. It costs $2.50 in, $15 out per million tokens.
- 46th of 123 rated models
- Rating 1,379
- Rated on 15 benchmarks
- Closed
- Released Mar 5, 2026
- 1.1 million tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 11th of 15 on Legal Agent Benchmark
- 23rd of 33 on MCP Atlas
- 58th of 98 on LMArena WebDev
Price: $2.50 in, $15 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- APEX-Agents52.4%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
30th of 56. Independent result from Epoch AI.
- BrowseComp82.7%
Questions whose answers are hidden deep on the web and take many searches and pages to track down.
20th of 56. The maker's own number, from OpenAI, via LLM Stats.
- MCP Atlas67.2%
Multi-step tasks where the model has to pick and combine many real tools, connected through MCP, the standard way agents plug into apps and data.
23rd of 33. The maker's own number, from OpenAI, via LLM Stats.
- SWE-Bench Pro57.7%
Long changes to real codebases in several languages, often across many files, including code from private and copyleft projects that models are unlikely to have seen.
25th of 50. The maker's own number, from OpenAI, via LLM Stats.
- Humanity's Last Exam36.2%
About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.
Independent result from Epoch AI.
- Vending-Bench 2$6,144
The model runs a simulated vending machine business for a year on its own: finding suppliers, ordering stock, setting prices and paying the daily fees.
24th of 60. Independent result from Epoch AI.
- OSWorld-Verified75%
Ordinary tasks on a real desktop computer using normal apps: a browser, a spreadsheet, an email client, a photo editor, the file manager.
12th of 25. The maker's own number, from OpenAI, via LLM Stats.
- Toolathlon54.6%
Long tasks across many real apps and their tools, such as email, calendars, spreadsheets, code repositories and online stores.
13th of 37. The maker's own number, from OpenAI, via LLM Stats.
- DeepSWE 1.152%
Software engineering tasks run in the same simple agent setup for every model.
Independent result from LLM Stats.
- SimpleQA Verified45.1%
Short factual questions with one checked answer, asked without web search.
41st of 78. Independent result from Epoch AI.
12 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.