modelbenchmark.io

Claude 4.5 Sonnet

Anthropic · claude-4-5-sonnet

Compare

Balanced Claude model for coding, analysis, agent workflows, and cost control

Specification

most-agreed values

Context
200K
Max output
64K
Released
2025-09-30
Knowledge cutoff
2025-09
Retires
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$3.00
Output
$15.00
Cache read
$0.30
Cache write
$3.75

Quality

1 benchmark · 1 source

Composite
87th
percentile of 334 scored models
Rank
46 / 334
±0.10 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
1.3
points between effort settings
coding71st1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified72.7default · mini-SWE-agent · 2 runsSWE-bench
71.4high · mini-SWE-agentSWE-bench
Settings differ by 1.3 points on this benchmark.

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
cortecs$2.989$14.945$0.326$4.078200K64K
helicone$3.00$15.00$0.30$3.75200K64K
replicate · replicate$3.00$15.00
qiniu-ai200K64K

More from Anthropic

most-hosted first