Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
Claude Sonnet 4
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Evaluations
Evaluation overview
Overall rank
#68
70.4 points · 180 models
Coding rank
#69
71.3 points · 160 models
Data coverage
17 items
2 sources · updated through 2025-07-22
Domain performance
Coding
#69 / 160
71.3
Agents
#55 / 125
69.5
Evaluation highlights
All evaluations
BFCL v3 Full
Agents · Qwen3-Coder Technical Report
73.3%
3
/ 49
SWE-bench Verified OpenHands 100 turns
Coding · Qwen3-Coder Technical Report
68%
1
/ 5
TAU-bench Retail
Agents · Qwen3-Coder Technical Report
80.5%
1
/ 15
TAU-bench Airline
Agents · Qwen3-Coder Technical Report
60%
3
/ 15
Spider2
Agents · Qwen3-Coder Technical Report
31.1%
1
/ 5
WebArena
Agents · Qwen3-Coder Technical Report
51.1%
1
/ 5
Basic information
Context (input / output)
200K / 64K
Release date
2025-05
Input modalities
Text · Image
Output modalities
Text
Related links
Official site
Version relationships
Claude Sonnet 4 family
Claude Sonnet 4
Current
2025-05 · Current model
Claude Sonnet 4.5
2025-09 · Same series
Claude Sonnet 4.6
2026-02 · Same series