Back to all LLMs

Claude Sonnet 4.5

Strong coding and analysis capabilities with 200K context window and prompt caching for efficient RAG workflows. Balanced performance for production applications. If you want to compare the best LLMs for your data, try Agentset.

Leaderboard Rank
#8
of 14
ELO Rating
1533
#8
Win Rate
39.0%
#9
Latency
9659ms
#6

Model Information

Provider
Anthropic
License
Proprietary
Input Price per 1M
$3.00
Output Price per 1M
$15.00
Context Window
200K
Release Date
2025-09-29
Model Name
claude-sonnet-4.5
Total Evaluations
1170

Performance Record

Wins456 (39.0%)
Losses525 (44.9%)
Ties189 (16.2%)
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

Claude Sonnet 4.5's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

Claude Sonnet 4.5 - ELO by Dataset

Detailed Metrics

Dataset breakdown

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

SciFact

ELO 173548.7% WR190W-91L-109T

Quality Metrics

Correctness
4.80
Faithfulness
4.87
Grounding
4.77
Relevance
5.00
Completeness
4.73
Overall
4.83

Latency Distribution

Mean
6830ms
Min
2621ms
Max
10722ms

MSMARCO

ELO 157246.2% WR180W-149L-61T

Quality Metrics

Correctness
4.87
Faithfulness
4.87
Grounding
4.87
Relevance
4.93
Completeness
4.87
Overall
4.88

Latency Distribution

Mean
9825ms
Min
2325ms
Max
21762ms

PG

ELO 129422.1% WR86W-285L-19T

Quality Metrics

Correctness
5.00
Faithfulness
5.00
Grounding
5.00
Relevance
5.00
Completeness
5.00
Overall
5.00

Latency Distribution

Mean
12322ms
Min
9247ms
Max
20544ms

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 Claude Sonnet 4.5 with other top llms to understand the differences in performance, accuracy, and latency.