Index · Agentic terminal use
Terminal-Bench Core 0.1.1
80 tasks indexed.
- blind-maze-explorer-5x5
- blind-maze-explorer-algorithm
- blind-maze-explorer-algorithm.easy
- blind-maze-explorer-algorithm.hard
- build-initramfs-qemu
- build-linux-kernel-qemu
- build-tcc-qemu
- cartpole-rl-training
- chess-best-move
- conda-env-conflict-resolution
- configure-git-webserver
- count-dataset-tokens
- crack-7z-hash
- crack-7z-hash.easy
- crack-7z-hash.hard
- create-bucket
- cron-broken-network
- csv-to-parquet
- decommissioning-service-with-sensitive-data
- download-youtube
- eval-mteb
- eval-mteb.hard
- extract-moves-from-video
- extract-safely
- fibonacci-server
- fix-git
- fix-pandas-version
- fix-permissions
- get-bitcoin-nodes
- git-multibranch
- git-workflow-hack
- gpt2-codegolf
- grid-pattern-transform
- hello-world
- heterogeneous-dates
- hf-model-inference
- incompatible-python-fasttext
- incompatible-python-fasttext.base_with_hint
- intrusion-detection
- jupyter-notebook-server
- modernize-fortran-build
- new-encrypt-command
- nginx-request-logging
- oom
- openssl-selfsigned-cert
- organization-json-generator
- password-recovery
- path-tracing-reverse
- path-tracing
- play-zork
- polyglot-c-py
- polyglot-rust-c
- processing-pipeline
- prove-plus-comm
- pytorch-model-cli
- pytorch-model-cli.easy
- pytorch-model-cli.hard
- qemu-alpine-ssh
- qemu-startup
- raman-fitting
- raman-fitting.easy
- reshard-c4-data
- run-pdp11-code
- sanitize-git-repo
- sanitize-git-repo.hard
- security-vulhub-minio
- simple-sheets-put
- simple-web-scraper
- solana-data
- sqlite-db-truncate
- sqlite-with-gcov
- super-benchmark-upet
- swe-bench-astropy-1
- swe-bench-astropy-2
- swe-bench-fsspec
- swe-bench-langcodes
- tmux-advanced-workflow
- train-fasttext
- vim-terminal-task
- write-compressor