Index · Agentic terminal use
Terminal-Bench 2.0
89 tasks indexed.
- adaptive-rejection-sampler
- bn-fit-modify
- break-filter-js-from-html
- build-cython-ext
- build-pmars
- build-pov-ray
- caffe-cifar-10
- cancel-async-tasks
- chess-best-move
- circuit-fibsqrt
- cobol-modernization
- code-from-image
- compile-compcert
- configure-git-webserver
- constraints-scheduling
- count-dataset-tokens
- crack-7z-hash
- custom-memory-heap-crash
- db-wal-recovery
- distribution-search
- dna-assembly
- dna-insert
- extract-elf
- extract-moves-from-video
- feal-differential-cryptanalysis
- feal-linear-cryptanalysis
- filter-js-from-html
- financial-document-processor
- fix-code-vulnerability
- fix-git
- fix-ocaml-gc
- gcode-to-text
- git-leak-recovery
- git-multibranch
- gpt2-codegolf
- headless-terminal
- hf-model-inference
- install-windows-3.11
- kv-store-grpc
- large-scale-text-editing
- largest-eigenval
- llm-inference-batching-scheduler
- log-summary-date-ranges
- mailman
- make-doom-for-mips
- make-mips-interpreter
- mcmc-sampling-stan
- merge-diff-arc-agi-task
- model-extraction-relu-logits
- modernize-scientific-stack
- mteb-leaderboard
- mteb-retrieve
- multi-source-data-merger
- nginx-request-logging
- openssl-selfsigned-cert
- overfull-hbox
- password-recovery
- path-tracing
- path-tracing-reverse
- polyglot-c-py
- polyglot-rust-c
- portfolio-optimization
- protein-assembly
- prove-plus-comm
- pypi-server
- pytorch-model-cli
- pytorch-model-recovery
- qemu-alpine-ssh
- qemu-startup
- query-optimize
- raman-fitting
- regex-chess
- regex-log
- reshard-c4-data
- rstan-to-pystan
- sam-cell-seg
- sanitize-git-repo
- schemelike-metacircular-eval
- sparql-university
- sqlite-db-truncate
- sqlite-with-gcov
- torch-pipeline-parallelism
- torch-tensor-parallelism
- train-fasttext
- tune-mjcf
- video-processing
- vulnerable-secret
- winning-avg-corewars
- write-compressor