Atlas Graph Explorer
Wiki
Graph
Edges
Home
Benchmark
benchmark:terminal-bench
Terminal-Bench
benchmark:terminal-bench
Benchmark
benchmarks/benchmarks/terminal-bench.yaml
·
Open in Graph →
overview
json
graph
Attributes
displayName
Terminal-Bench
homepageUrl
https://www.tbench.ai/
kind
terminal-agent
targetsKind
AgentVersion
description
Benchmark for AI agents performing real software-engineering and devops tasks in a terminal environment.
Outgoing edges
(1)
covers
1
skill-area:cli-design
·
SkillArea
CLI Design
Incoming edges
(3)
belongs_to_benchmark
1
test-set:terminal-bench-v1
·
TestSet
Terminal-Bench v1
bounds_subject
1
scope-boundary:terminal-bench.scope
·
ScopeBoundary
for_benchmark
1
eval-run:terminal-bench.claude-sonnet-4-5.2025-09
·
EvalRun