Back to all LLMs

GPT-5.1

400K context with adaptive reasoning that allocates more processing to complex retrieved content. Extended prompt caching feature with longer retention optimizes performance for production RAG systems. If you want to compare the best LLMs for your data, try Agentset.

Leaderboard Rank
#3
of 16
ELO Rating
1689
#3
Win Rate
65.5%
#3
Latency
16192ms
#12

Model Information

Provider
OpenAI
License
Proprietary
Input Price per 1M
$1.25
Output Price per 1M
$10.00
Context Window
400K
Release Date
2025-11-13
Model Name
gpt-5.1
Total Evaluations
1350

Performance Record

Wins884 (65.5%)
Losses252 (18.7%)
Ties214 (15.9%)
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-5.1's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

GPT-5.1 - ELO by Dataset

Detailed Metrics

Dataset breakdown

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

PG

ELO 186885.1% WR383W-55L-12T

Quality Metrics

Correctness
5.00
Faithfulness
5.00
Grounding
5.00
Relevance
5.00
Completeness
4.77
Overall
4.95

Latency Distribution

Mean
29008ms
Min
4393ms
Max
43887ms

SciFact

ELO 160058.7% WR264W-61L-125T

Quality Metrics

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

Latency Distribution

Mean
10454ms
Min
4700ms
Max
21205ms

MSMARCO

ELO 159952.7% WR237W-136L-77T

Quality Metrics

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

Latency Distribution

Mean
9111ms
Min
3841ms
Max
34731ms

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);
}