Agentic AI Atlas

IV.

Edge detail

belongs_to_benchmark

Page 1 of 1

belongs_to_benchmark ledger

a TestSet belongs to a Benchmark (the benchmark it tests against)

Pairs · 25Cardinality · N:1

from	to	to kind
test-set:bigcode-evalplus	benchmark:bigcode-evalplus	Benchmark
test-set:gsm8k-test	benchmark:gsm8k	Benchmark
test-set:hellaswag-validation	benchmark:hellaswag	Benchmark
test-set:livecodebench-2024-12	benchmark:livecodebench	Benchmark
test-set:math-test	benchmark:math	Benchmark
test-set:swe-bench-original	benchmark:swe-bench	Benchmark
test-set:webarena-v1	benchmark:webarena	Benchmark
test-set:tau-bench-airline-retail	benchmark:tau-bench	Benchmark
test-set:bigcodebench-full	benchmark:bigcodebench	Benchmark
test-set:ds1000-full	benchmark:ds1000	Benchmark
test-set:mle-bench-competitions	benchmark:mle-bench	Benchmark
test-set:humaneval-original	benchmark:human-eval	Benchmark
test-set:mbpp-full	benchmark:mbpp	Benchmark
test-set:agentbench-environments	benchmark:agentbench	Benchmark
test-set:toolbench-tooleval	benchmark:toolbench	Benchmark
test-set:osworld-369-computer-tasks	benchmark:os-world	Benchmark
test-set:androidworld-programmatic-tasks	benchmark:android-world	Benchmark
test-set:appworld-750-cross-app-tasks	benchmark:appworld	Benchmark
test-set:assistantbench-214-web-tasks	benchmark:assistant-bench	Benchmark
test-set:re-bench-ai-rd-tasks	benchmark:re-bench	Benchmark
test-set:travelplanner-planning-intents	benchmark:travelplanner	Benchmark
test-set:the-agent-company-workplace-tasks	benchmark:the-agent-company	Benchmark
test-set:agentclinic-clinical-cases	benchmark:agentclinic	Benchmark
test-set:swe-bench-verified-2024-12	benchmark:swe-bench-verified	Benchmark
test-set:terminal-bench-v1	benchmark:terminal-bench	Benchmark