Back to all LLMs

GPT-5.4 Pro

Deep reasoning model that uses more compute to think harder. Produces smarter and more precise responses for complex tasks. Operates via Responses API with multi-turn reasoning - some requests may take several minutes. Does not support structured outputs or fine-tuning. If you want to compare the best LLMs for your data, try Agentset.

Leaderboard Rank
#13
of 16
ELO Rating
1330
#13
Win Rate
24.6%
#13
Latency
75663ms
#16

Model Information

Provider
OpenAI
License
Proprietary
Input Price per 1M
$30.00
Output Price per 1M
$180.00
Context Window
1050K
Release Date
2026-03-05
Model Name
gpt-5.4-pro
Total Evaluations
1350

Performance Record

Wins332 (24.6%)
Losses846 (62.7%)
Ties172 (12.7%)
Wins
Losses
Ties

LLMs Are Just One Piece of RAG

Agentset gives you a managed RAG pipeline with the top-ranked models and best practices baked in. No infrastructure to maintain, no LLM orchestration to manage.

Trusted by teams building production RAG applications

5M+
Documents
1,500+
Teams
99.9%
Uptime

Performance Overview

ELO ratings by dataset

GPT-5.4 Pro's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

GPT-5.4 Pro - ELO by Dataset

Detailed Metrics

Dataset breakdown

Performance metrics across different benchmark datasets, including accuracy and latency percentiles.

SciFact

ELO 150727.6% WR124W-230L-96T

Quality Metrics

Correctness
4.87
Faithfulness
4.90
Grounding
4.87
Relevance
4.93
Completeness
4.87
Overall
4.89

Latency Distribution

Mean
2148ms
Min
1111ms
Max
3838ms

PG

ELO 127730.2% WR136W-289L-25T

Quality Metrics

Correctness
5.00
Faithfulness
5.00
Grounding
5.00
Relevance
5.00
Completeness
4.97
Overall
4.99

Latency Distribution

Mean
156451ms
Min
57901ms
Max
250411ms

MSMARCO

ELO 120716.0% WR72W-327L-51T

Quality Metrics

Correctness
4.97
Faithfulness
5.00
Grounding
5.00
Relevance
4.93
Completeness
4.73
Overall
4.93

Latency Distribution

Mean
68388ms
Min
8911ms
Max
165229ms

Build RAG in Minutes, Not Months

Agentset gives you a complete RAG API with top-ranked LLMs and smart retrieval built in. Upload your data, call the API, and get grounded answers from day one.

import { Agentset } from "agentset";

const agentset = new Agentset();
const ns = agentset.namespace("ns_1234");

const results = await ns.search(
  "What is multi-head attention?"
);

for (const result of results) {
  console.log(result.text);
}

Compare Models

See how it stacks up

Compare GPT-5.4 Pro with other top llms to understand the differences in performance, accuracy, and latency.