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
Benchmark details loading
Back to benchmarks
Terminal-Bench 4.0
Coding
Agents
Share
Official website
Results for 28 models collected from 17 public sources.
Ranking
Sources
#
Model
Score
1
Claude Sonnet 5.5
Anthropic
70.6
%
2
Claude Opus 5.5
Anthropic
66.4
%
3
Kimi K3.1 Pro
Moonshot AI
65.7
%
4
GPT-6 Astra
OpenAI
58.2
%
5
Claude Fable 5.1
Anthropic
57.9
%
6
Gemini 4 Argon
Google
57.4
%
7
Claude Opus 5
Anthropic
52.3
%
8
Muse Wonder
Meta
52.0
%
9
GPT-6.1 Terra
OpenAI · max
50.3
%
10
Hunyuan 4
Tencent
44.4
%
28 models total
1
2
3