Terminal-Bench 2 Verified

Verified subset of Terminal-Bench 2 tasks.

Terminal-Bench 2 Verified is the verified subset of Terminal-Bench 2 tasks.

Runtime Status

Field	Value
Benchmark id	terminal_bench_2_verified
Tags	Terminal, Tool Use, Verified
Execution type	remote environment
Typical harness	terminus2
Typical environment	modal, daytona, or cluster provider
Current status	registered in the direct runtime

Run Example

agentcompass run \
  terminal_bench_2_verified \
  terminus2 \
  your-model \
  --env <env-provider> \
  --benchmark-params '{"sample_ids":["<task-id>"]}' \
  --model-base-url "$MODEL_BASE_URL" \
  --model-api-key "$MODEL_API_KEY"

Recipes can infer task images and use /root as the Terminal-Bench workspace root.

Outputs

Per-task details are written to results/terminal_bench_2_verified/<model>/<run>/details/. Aggregate metrics are written to summary.md.