Claude Sonnet 5 Benchmark Details

Claude Sonnet 5 currently shows benchmark results led by HLE (7 / 164, score 57.40), SWE-bench Verified (6 / 109, score 85.20), BrowseComp (5 / 49, score 84.70). 1 source link is attached for reference.

Benchmark Results

Claude Sonnet 5

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

HLE

Thinking Level · Extra High

43.20

43 / 164

HLE

Thinking Level · Extra HighTools

57.40

7 / 164

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

Thinking Level · Extra HighTools

85.20

6 / 109

DeepSWE

DeepTools

7 / 16

AI Agent - Information Search

1 evaluations

Benchmark / mode

Score

Rank/total

BrowseComp

Thinking EnabledToolsInternet

84.70

5 / 49

AI Agent - Tool Usage

2 evaluations

Benchmark / mode

Score

Rank/total

OSWorld-Verified

Thinking Level · Extra HighTools

81.20

3 / 20

TerminalBench 2.1

Thinking Level · Extra HighTools

80.40

9 / 21

Compare with other models

Sources

anthropic.comanthropic.com