Inference
Explore
Leaderboard
Benchmarks
Labs
Run locally
Search
⌘K
EN
English
Русский
Локально
中文
本地运行
12 Nov
2026
Benchmarks
/
terminalBench3
terminalBench3
Not in index
Agentic
Best in agentic
Models
?
Models with a result.
2
Top result
?
Best result on this benchmark.
—
Top-3 spread
?
Points from first to third.
—
Year
?
Year of release.
—
Results
2 results
Export
CSV
Export
JSON
#
Model
Result
?
The score from the source.
—
DeepSeek V4.1 Flash 1017
30.0
%
—
GLM-5.3
28.3
%