Dataset package
UPSTREAM SOURCES & DISCOVERY
Follow the upstream
registries.
490 upstream records across 5 sources: environment manifests, dataset packages, configurations and coding examples, with snapshot and version metadata.
These are automatically captured metadata records, without individual project review or execution verification. Versions, forks and wrappers can overlap; do not add this count to the reviewed project count.
Environment manifest
Benchmark configuration
Foundation project
Coding example manifest
Search upstream records
71 records link to related project notesCombine keywords; put an exact phrase in double quotes.
| Name / related notes | Observed metadata | Source / captured |
|---|---|---|
| aarr/aarri-bench#Dataset package | Observed r1 · 82 registered tasks | Harbor Hub ↗ |
| abhishek203/task-aw#Dataset package | Observed r1 · 5 registered tasks | Harbor Hub ↗ |
| abundant/swe-gen-cpp#Dataset package | Observed r1 · 999 registered tasks | Harbor Hub ↗ |
| abundant/swe-gen-go#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| abundant/swe-gen-java#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| abundant/swe-gen-js#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| abundant/swe-gen-rust#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| abundant/swe-marathon#Dataset package | Observed r2 · 20 registered tasks | Harbor Hub ↗ |
| actava-ai/chi-bench#Dataset package | Observed r15 · 78 registered tasks | Harbor Hub ↗ |
| adameubanks/rating-generation-consistency#Dataset package | Observed r1 · 45 registered tasks | Harbor Hub ↗ |
| adyen/dabstep#Dataset package | Observed r1 · 450 registered tasks | Harbor Hub ↗ |
| agent_world_model_env#Environment manifest | envs/agent_world_model_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| agentic-labs/erp-bench#Dataset package | Observed r1 · 300 registered tasks | Harbor Hub ↗ |
| agentscope-ai/pawbench#Dataset package | Observed r4 · 150 registered tasks | Harbor Hub ↗ |
| ai-forever/harness-bench-fast#Dataset package | Observed r1 · 231 registered tasks | Harbor Hub ↗ |
| aider/aider-polyglot#Dataset package | Observed r1 · 225 registered tasks | Harbor Hub ↗ |
| aime/aime#Dataset package | Observed r1 · 60 registered tasks | Harbor Hub ↗ |
| ale/rsi-post-training#Dataset package | Observed r11 · 6 registered tasks | Harbor Hub ↗ |
| algotune/algotune#Dataset package | Observed r1 · 154 registered tasks | Harbor Hub ↗ |
| alibaba-aaig/alibaba-ctf#Dataset package | Observed r14 · 87 registered tasks | Harbor Hub ↗ |
| android-bench/android-bench#Dataset package | Observed r5 · 100 registered tasks | Harbor Hub ↗ |
| apple/mmau#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| Arcade Learning Environment#Foundation project | Upstream category: incubating | Farama Foundation ↗ |
| arcprize/arc-agi-2#Dataset package | Observed r1 · 167 registered tasks | Harbor Hub ↗ |
| arcus-labs/tau3-banking#Dataset package | Observed r1 · 97 registered tasks | Harbor Hub ↗ |
| arcus-labs/tau3-banking-dev#Dataset package | Observed r2 · 30 registered tasks | Harbor Hub ↗ |
| arcus-labs/tau3-banking-test#Dataset package | Observed r2 · 30 registered tasks | Harbor Hub ↗ |
| artisan-csa#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| aryaniyaps/lamina-bench#Dataset package | Observed r2 · 20 registered tasks | Harbor Hub ↗ |
| ashantanu/task1_v3_1_stock_research_basket_rolling#Dataset package | Observed r1 · 8 registered tasks | Harbor Hub ↗ |
| assistantbench#Benchmark configuration | Configuration: assistantbench | BrowserGym ↗ |
| asteroid-game#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| asteroid-game-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| atari_env#Environment manifest | envs/atari_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| atm-bench/atm-bench-hard-sgm#Dataset package | Observed r1 · 31 registered tasks | Harbor Hub ↗ |
| au12321ua/cadir-ci-benchmark#Dataset package | Observed r3 · 2 registered tasks | Harbor Hub ↗ |
| au12321ua/mesh2cad-smoke#Dataset package | Observed r1 · 6 registered tasks | Harbor Hub ↗ |
| audio-step-sequencer#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| bauerjustin/tb3-preview-v2#Dataset package | Observed r2 · 111 registered tasks | Harbor Hub ↗ |
| bauerjustin/terminal-bench-3-test#Dataset package | Observed r2 · 64 registered tasks | Harbor Hub ↗ |
| bencalvert04/programbench#Dataset package | Observed r2 · 200 registered tasks | Harbor Hub ↗ |
| benchflow/skillsbench#Dataset package | Observed r3 · 87 registered tasks | Harbor Hub ↗ |
| bespokelabs/autoresearch-exam#Dataset package | Observed r7 · 29 registered tasks | Harbor Hub ↗ |
| bigcode/bigcodebench-hard-complete#Dataset package | Observed r1 · 145 registered tasks | Harbor Hub ↗ |
| bigcode/humanevalfix#Dataset package | Observed r1 · 164 registered tasks | Harbor Hub ↗ |
| billxbf/mimo-v26-code#Dataset package | Observed r2 · 2,698 registered tasks | Harbor Hub ↗ |
| billxbf/mimo-v26-cyber#Dataset package | Observed r2 · 1,000 registered tasks | Harbor Hub ↗ |
| billxbf/mimo-v26-general#Dataset package | Observed r2 · 925 registered tasks | Harbor Hub ↗ |
| billxbf/mimo-v26-music#Dataset package | Observed r2 · 1,000 registered tasks | Harbor Hub ↗ |
| billxbf/mimo-v26-terminal#Dataset package | Observed r2 · 64 registered tasks | Harbor Hub ↗ |
| billxbf/mimo-v26-webdev#Dataset package | Observed r2 · 2,093 registered tasks | Harbor Hub ↗ |
| billxbf/terminal-agent-mix#Dataset package | Observed r3 · 9,207 registered tasks | Harbor Hub ↗ |
| billxbf/terminal-agent-mix-light#Dataset package | Observed r1 · 3,064 registered tasks | Harbor Hub ↗ |
| binary-audit/binary-audit#Dataset package | Observed r1 · 46 registered tasks | Harbor Hub ↗ |
| biopharma-bench/biopharma-bench#Dataset package | Observed r1 · 10 registered tasks | Harbor Hub ↗ |
| blobfishai/arc-crm-6#Dataset package | Observed r3 · 6 registered tasks | Harbor Hub ↗ |
| blobfishai/counselbench-100#Dataset package | Observed r7 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/dealbench-100-suite#Dataset package | Observed r3 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/devopsbench-100#Dataset package | Observed r8 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/domainbench-24#Dataset package | Observed r9 · 24 registered tasks | Harbor Hub ↗ |
| blobfishai/erpbench-100-suite#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/factorybench-100#Dataset package | Observed r9 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/hubbench#Dataset package | Observed r5 · 104 registered tasks | Harbor Hub ↗ |
| blobfishai/ledgerbench-100#Dataset package | Observed r6 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/litigation#Dataset package | Observed r2 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/salesbench-100#Dataset package | Observed r9 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/semikongbench-100#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| blobfishai/webbench#Dataset package | Observed r4 · 159 registered tasks | Harbor Hub ↗ |
| brando90/vb-generation-one-20260913#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| browsergym_env#Environment manifest | envs/browsergym_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| brutalist-dev-landing-page#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| brutalist-dev-landing-page-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| cais/swebenchpro#Dataset package | Observed r2 · 731 registered tasks | Harbor Hub ↗ |
| calendar_env#Environment manifest | envs/calendar_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| camel-ai/seta-env#Dataset package | Observed r1 · 1,376 registered tasks | Harbor Hub ↗ |
| camping-gear-checklist#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| camping-gear-checklist-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| carla_env#Environment manifest | envs/carla_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| case-study-landing-page#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| chat_env#Environment manifest | envs/chat_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| chess_env#Environment manifest | envs/chess_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| cloud-painter#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| cmu/refav#Dataset package | Observed r2 · 1,500 registered tasks | Harbor Hub ↗ |
| codepde/codepde#Dataset package | Observed r1 · 5 registered tasks | Harbor Hub ↗ |
| coding_env#Environment manifest | envs/coding_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| coding_tools_env#Environment manifest | envs/coding_tools_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| cohere/terminal_bench_aai#Dataset package | Observed r1 · 44 registered tasks | Harbor Hub ↗ |
| color-match-challenge#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| company-acronym-list#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| connect4_env#Environment manifest | envs/connect4_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| cookbook/test#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| crustbench/crustbench#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| csv-to-charts#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| customer-journey-flow#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| customer-journey-flow-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| datacurve/deep-swe#Dataset package | Observed r2 · 113 registered tasks | Harbor Hub ↗ |
| datacurve/deep-swe-1-1#Dataset package | Observed r1 · 113 registered tasks | Harbor Hub ↗ |
| dbt-labs/ade-bench#Dataset package | Observed r1 · 48 registered tasks | Harbor Hub ↗ |
| deveval/deveval#Dataset package | Observed r1 · 63 registered tasks | Harbor Hub ↗ |
| dipg_safety_env#Environment manifest | envs/dipg_safety_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| dissei/financial-judgment-full#Dataset package | Observed r5 · 7 registered tasks | Harbor Hub ↗ |
| diyakejriwal/finsearchcomp-t2-global#Dataset package | Observed r2 · 119 registered tasks | Harbor Hub ↗ |
| dm_control_env#Environment manifest | envs/dm_control_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| doe/legal-consent-sweep#Dataset package | Observed r5 · 1 registered tasks | Harbor Hub ↗ |
| doe/sample-pack#Dataset package | Observed r2 · 5 registered tasks | Harbor Hub ↗ |
| drugtargetbench/drugtargetbench#Dataset package | Observed r5 · 60 registered tasks | Harbor Hub ↗ |
| echo_env#Environment manifest | envs/echo_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| elfsong/cpu2gpu#Dataset package | Observed r10 · 258 registered tasks | Harbor Hub ↗ |
| elfsong/mercury-eval#Dataset package | Observed r1 · 256 registered tasks | Harbor Hub ↗ |
| employee-skills-matrix#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| employee-skills-matrix-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| Enterprise-Bench/l1-l2-bench#Dataset package | Observed r5 · 14 registered tasks | Harbor Hub ↗ |
| equation-solver-tool#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| escape-the-maze#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| esports-tournament-landing-page#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| espresso#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| evaligo/swe-race#Dataset package | Observed r1 · 94 registered tasks | Harbor Hub ↗ |
| event-count-down#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| event-feedback#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| evoeval/evoeval#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| factory-ai/legacy-bench#Dataset package | Observed r1 · 10 registered tasks | Harbor Hub ↗ |
| falling-object-catcher#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| farewell-message-board#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| featurebench/featurebench#Dataset package | Observed r1 · 200 registered tasks | Harbor Hub ↗ |
| featurebench/featurebench-lite#Dataset package | Observed r1 · 30 registered tasks | Harbor Hub ↗ |
| featurebench/featurebench-lite-modal#Dataset package | Observed r1 · 30 registered tasks | Harbor Hub ↗ |
| featurebench/featurebench-modal#Dataset package | Observed r1 · 200 registered tasks | Harbor Hub ↗ |
| festival-lights-show#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| finqa_env#Environment manifest | envs/finqa_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| finrl_env#Environment manifest | envs/finrl_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| fritzprix/libragent-browser-dual-12#Dataset package | Observed r1 · 12 registered tasks | Harbor Hub ↗ |
| fritzprix/libragent-compaction-fact-recall-1#Dataset package | Observed r6 · 3 registered tasks | Harbor Hub ↗ |
| fritzprix/libragent-diverse-9#Dataset package | Observed r2 · 9 registered tasks | Harbor Hub ↗ |
| fritzprix/libragent-knowledge-bridge-2#Dataset package | Observed r1 · 2 registered tasks | Harbor Hub ↗ |
| fritzprix/libragent-media-desktop-10#Dataset package | Observed r3 · 10 registered tasks | Harbor Hub ↗ |
| fritzprix/libragent-org-collab-7#Dataset package | Observed r2 · 7 registered tasks | Harbor Hub ↗ |
| fritzprix/libragent-swe-diverse-8#Dataset package | Observed r1 · 8 registered tasks | Harbor Hub ↗ |
| frontier-harness-eval/frontier-harness-eval#Dataset package | Observed r6 · 62 registered tasks | Harbor Hub ↗ |
| frontis/agent-obs-core#Dataset package | Observed r7 · 3 registered tasks | Harbor Hub ↗ |
| frontis/generated-basic-production-traces#Dataset package | Observed r8 · 57 registered tasks | Harbor Hub ↗ |
| fun-game#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| futurehouse/bixbench#Dataset package | Observed r1 · 205 registered tasks | Harbor Hub ↗ |
| futurehouse/bixbench-cli#Dataset package | Observed r1 · 205 registered tasks | Harbor Hub ↗ |
| futurehouse/labbench#Dataset package | Observed r1 · 181 registered tasks | Harbor Hub ↗ |
| gabeorlanski/slopcodebench#Dataset package | Observed r4 · 36 registered tasks | Harbor Hub ↗ |
| gaia/gaia#Dataset package | Observed r1 · 165 registered tasks | Harbor Hub ↗ |
| git_env#Environment manifest | envs/git_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| gnucleus-ai/cad-bench#Dataset package | Observed r3 · 100 registered tasks | Harbor Hub ↗ |
| gorilla/bfcl#Dataset package | Observed r1 · 3,641 registered tasks | Harbor Hub ↗ |
| gorilla/bfcl_parity#Dataset package | Observed r1 · 123 registered tasks | Harbor Hub ↗ |
| gpqa-diamond/gpqa-diamond#Dataset package | Observed r1 · 198 registered tasks | Harbor Hub ↗ |
| grafana/o11y-bench#Dataset package | Observed r1 · 63 registered tasks | Harbor Hub ↗ |
| grandsmile/unicode#Dataset package | Observed r1 · 399 registered tasks | Harbor Hub ↗ |
| grid_world_env#Environment manifest | envs/grid_world_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| gustofied/compute-bazaar-bench#Dataset package | Observed r5 · 4 registered tasks | Harbor Hub ↗ |
| Gymnasium#Foundation project | Upstream category: core | Farama Foundation ↗ |
| Gymnasium-Robotics#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| hack-verifiable-environments/hv-terminal-bench-2-1#Dataset package | Observed r4 · 89 registered tasks | Harbor Hub ↗ |
| handshake-ai/atlas-finance#Dataset package | Observed r7 · 100 registered tasks | Harbor Hub ↗ |
| harbor-index/harbor-index#Dataset package | Observed r5 · 80 registered tasks | Harbor Hub ↗ |
| harbor-index/harbor-index-1.0#Dataset package | Observed r1 · 82 registered tasks | Harbor Hub ↗ |
| harbor/hello-world#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| harbor_env#Environment manifest | envs/harbor_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| harveyai/lab#Dataset package | Observed r1 · 1,251 registered tasks | Harbor Hub ↗ |
| healthy-meal-tracker#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| helium_browser_env#Environment manifest | envs/helium_browser_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| heytalal/maydan-hf-rl-sampler#Dataset package | Observed r1 · 10 registered tasks | Harbor Hub ↗ |
| HighwayEnv#Foundation project | Upstream category: incubating | Farama Foundation ↗ |
| holiday-card-for-kids#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| holiday-card-for-kids-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| huu256/gauntlet#Dataset package | Observed r1 · 5 registered tasks | Harbor Hub ↗ |
| huu256/gauntlet-planner#Dataset package | Observed r1 · 5 registered tasks | Harbor Hub ↗ |
| hwe-bench/hwe-bench#Dataset package | Observed r3 · 77 registered tasks | Harbor Hub ↗ |
| ibragim-badertdinov/swe-rebench-07-2026#Dataset package | Observed r1 · 111 registered tasks | Harbor Hub ↗ |
| ineqmath/ineqmath#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| infra-bench/infra-bench-v1#Dataset package | Observed r1 · 20 registered tasks | Harbor Hub ↗ |
| interactive-world-clock#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| islo-labs/reward-hack-bench#Dataset package | Observed r2 · 8 registered tasks | Harbor Hub ↗ |
| islo-labs/reward-hack-bench-control#Dataset package | Observed r2 · 8 registered tasks | Harbor Hub ↗ |
| itmo-autods/fdata-exit-case#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| itmo-autods/maize-yield-case#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| itmo-autods/openpoly-tg-case#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| itmo-autods/scientific-cases#Dataset package | Observed r1 · 3 registered tasks | Harbor Hub ↗ |
| ivanleo/agent-search#Dataset package | Observed r5 · 20 registered tasks | Harbor Hub ↗ |
| josancamon19/physician-bench#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| julia_env#Environment manifest | envs/julia_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| jupyter_env#Environment manifest | envs/jupyter_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| kernrl#Environment manifest | envs/kernrl/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| kgmon/deepsearchqa#Dataset package | Observed r2 · 900 registered tasks | Harbor Hub ↗ |
| kinetic-typography-studio#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| klinikebench/klinikebench#Dataset package | Observed r5 · 333 registered tasks | Harbor Hub ↗ |
| knows#Benchmark configuration | Configuration: knows | BrowserGym ↗ |
| kumo/kumo-1#Dataset package | Observed r1 · 5,300 registered tasks | Harbor Hub ↗ |
| kumo/kumo-easy#Dataset package | Observed r1 · 5,050 registered tasks | Harbor Hub ↗ |
| kumo/kumo-hard#Dataset package | Observed r1 · 250 registered tasks | Harbor Hub ↗ |
| kumo/kumo-parity#Dataset package | Observed r1 · 212 registered tasks | Harbor Hub ↗ |
| lamina/product-bench#Dataset package | Observed r7 · 12 registered tasks | Harbor Hub ↗ |
| language-learning-flashcards#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| last-secure-code-benchmark/last-secure-code-benchmark#Dataset package | Observed r3 · 450 registered tasks | Harbor Hub ↗ |
| lawbench/lawbench#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| lcb/longswebench-32k#Dataset package | Observed r4 · 3 registered tasks | Harbor Hub ↗ |
| lica-world/gdb#Dataset package | Observed r1 · 33,786 registered tasks | Harbor Hub ↗ |
| LiteCoder/LiteCoder-rl#Dataset package | Observed r2 · 602 registered tasks | Harbor Hub ↗ |
| livecodebench/livecodebench#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| looni-lab/smdd-bench#Dataset package | Observed r1 · 502 registered tasks | Harbor Hub ↗ |
| luosuu/SWE-kokkos-bench#Dataset package | Observed r8 · 100 registered tasks | Harbor Hub ↗ |
| MAgent2#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| markdown-to-slides#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| math-practice-drills#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| maxbittker/runebench#Dataset package | Observed r2 · 32 registered tasks | Harbor Hub ↗ |
| maze_env#Environment manifest | envs/maze_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| mercor/apex-agents-1-1#Dataset package | Observed r18 · 240 registered tasks | Harbor Hub ↗ |
| meta/mlgym-bench#Dataset package | Observed r1 · 12 registered tasks | Harbor Hub ↗ |
| Metaworld#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| MichaelY310/devopsgym#Dataset package | Observed r1 · 728 registered tasks | Harbor Hub ↗ |
| micro-habit-tracker#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| Minari#Foundation project | Upstream category: core | Farama Foundation ↗ |
| Minigrid#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| miniwob#Benchmark configuration | Configuration: miniwob | BrowserGym ↗ |
| miniwob_tiny_test#Benchmark configuration | Configuration: miniwob_tiny_test | BrowserGym ↗ |
| minnesotanlp/aar#Dataset package | Observed r1 · 1,400 registered tasks | Harbor Hub ↗ |
| mmtb/multimedia-terminalbench#Dataset package | Observed r1 · 105 registered tasks | Harbor Hub ↗ |
| MO-Gymnasium#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| MOMAland#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| MPE2#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| music-theory-trainer#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| nanoswe/swe-bench-verified#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| nl2repobench/nl2repobench#Dataset package | Observed r1 · 104 registered tasks | Harbor Hub ↗ |
| nlile/registry-history-20260908#Dataset package | Observed r2 · 1 registered tasks | Harbor Hub ↗ |
| nonprofit-impact-report#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| NovitaAI/tb21-code-debug#Dataset package | Observed r2 · 32 registered tasks | Harbor Hub ↗ |
| NovitaAI/tb21-data-science#Dataset package | Observed r2 · 26 registered tasks | Harbor Hub ↗ |
| NovitaAI/tb21-file-recovery#Dataset package | Observed r2 · 9 registered tasks | Harbor Hub ↗ |
| NovitaAI/tb21-systems-security#Dataset package | Observed r2 · 22 registered tasks | Harbor Hub ↗ |
| nvats/codeskills-bench#Dataset package | Observed r1 · 23 registered tasks | Harbor Hub ↗ |
| ocean-wave-simulation#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| ocean-wave-simulation-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| online-course-landing-page#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| online-poll-board#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| online-whiteboard#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| open-design/open-design#Dataset package | Observed r9 · 7 registered tasks | Harbor Hub ↗ |
| openai-fm-inspired#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| openai/mmmlu#Dataset package | Observed r1 · 150 registered tasks | Harbor Hub ↗ |
| openai/simpleqa#Dataset package | Observed r1 · 4,326 registered tasks | Harbor Hub ↗ |
| openai/swe-lancer-diamond-all#Dataset package | Observed r1 · 463 registered tasks | Harbor Hub ↗ |
| openai/swe-lancer-diamond-ic#Dataset package | Observed r1 · 198 registered tasks | Harbor Hub ↗ |
| openai/swe-lancer-diamond-manager#Dataset package | Observed r1 · 265 registered tasks | Harbor Hub ↗ |
| openapp_env#Environment manifest | envs/openapp_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| openspiel_env#Environment manifest | envs/openspiel_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| openthoughts/openthoughts-tblite#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-code-contests-noblock#Dataset package | Observed r1 · 8,728 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-flat25-pseudocode-v2#Dataset package | Observed r1 · 728 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-flat25-speed-bonus-v2#Dataset package | Observed r1 · 764 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-flat25-stackoverflow-v2#Dataset package | Observed r1 · 765 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-flat25-subtle-debug-v3#Dataset package | Observed r1 · 289 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rle-adversarial#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rle-detailed-v3#Dataset package | Observed r1 · 413 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rle-error-report-v3#Dataset package | Observed r1 · 261 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rle-github-issue-v3#Dataset package | Observed r1 · 264 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rle-heavy-padding-v2#Dataset package | Observed r1 · 784 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rle-minimal-instructions-v3#Dataset package | Observed r1 · 233 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-codenet-python-v2#Dataset package | Observed r1 · 10,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-crosscodeeval-csharp-v4#Dataset package | Observed r1 · 1,768 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-crosscodeeval-java#Dataset package | Observed r1 · 2,139 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-curriculum-easy#Dataset package | Observed r1 · 514 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-curriculum-hard#Dataset package | Observed r1 · 506 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-curriculum-medium#Dataset package | Observed r1 · 512 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-defects4j-v3-v4#Dataset package | Observed r1 · 216 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-e2egit-large#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-e2egit-v2#Dataset package | Observed r1 · 500 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-exercism-python-v2#Dataset package | Observed r1 · 133 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-ghactions-v3#Dataset package | Observed r1 · 9,930 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-issue#Dataset package | Observed r1 · 4,830 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-methods2test-large-v2#Dataset package | Observed r1 · 4,472 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-methods2test-large-v3#Dataset package | Observed r1 · 4,472 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-multifile#Dataset package | Observed r1 · 4,907 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-nemotron-cpp#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-nemotron-junit#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-pr#Dataset package | Observed r1 · 4,793 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-pr-v2#Dataset package | Observed r1 · 4,793 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-pymethods2test-large#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-pymethods2test-v3#Dataset package | Observed r1 · 500 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-scaffold-v2#Dataset package | Observed r1 · 4,861 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-bash-v3#Dataset package | Observed r1 · 9,384 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-bash-withtests-gpt5mini-v2#Dataset package | Observed r1 · 8,922 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-bash-withtests-v2#Dataset package | Observed r1 · 8,922 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-csharp-v5#Dataset package | Observed r1 · 9,485 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-dockerfile-gpt5mini-v3#Dataset package | Observed r1 · 4,137 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-dockerfile-v2#Dataset package | Observed r1 · 497 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-go-v4#Dataset package | Observed r1 · 2,313 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-jest-large#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-jest-v2#Dataset package | Observed r1 · 500 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-junit-v6#Dataset package | Observed r1 · 872 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-php-large-v6#Dataset package | Observed r1 · 3,789 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-php-v2-v6#Dataset package | Observed r1 · 438 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-pytest-large#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-pytest-v2#Dataset package | Observed r1 · 500 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-ruby-v2#Dataset package | Observed r1 · 8,627 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-stack-rust-v2#Dataset package | Observed r1 · 9,987 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-taco-v2#Dataset package | Observed r1 · 10,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-unitsyn-python-large#Dataset package | Observed r1 · 5,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-exp-rpt-unitsyn-python-v3#Dataset package | Observed r1 · 500 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-freelancer-projects-sandboxes-ta-rl-gpt-5-mini-v2#Dataset package | Observed r1 · 9,999 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-freelancer-projects-sandboxes-ta-rl-gpt-5-nano-v2#Dataset package | Observed r1 · 9,999 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-inferredbugs-sandboxes-verifier#Dataset package | Observed r1 · 9,991 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-llm-verifier-freelancer#Dataset package | Observed r1 · 10,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-baseline-uniform-v2#Dataset package | Observed r1 · 3,718 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h1-struggle-zone-v2#Dataset package | Observed r1 · 3,116 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h10-reward-binary-v2#Dataset package | Observed r1 · 2,862 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h10-reward-proportional-v2#Dataset package | Observed r1 · 2,873 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h10-reward-staged-v2#Dataset package | Observed r1 · 3,873 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h11-compositional-gradient-v2#Dataset package | Observed r1 · 3,873 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h11-single-skill-only-v2#Dataset package | Observed r1 · 2,873 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h2-language-balanced-v2#Dataset package | Observed r1 · 4,506 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h2-language-proportional#Dataset package | Observed r1 · 4,135 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h4-binary-easy#Dataset package | Observed r1 · 2,010 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h5-skill-diverse-v2#Dataset package | Observed r1 · 3,166 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h6-test-quality-top25#Dataset package | Observed r1 · 2,747 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h7-raw-volume-5k-v2#Dataset package | Observed r1 · 3,718 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h8-adversarial-tests-v2#Dataset package | Observed r1 · 2,873 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-mix-h8-original-tests-v2#Dataset package | Observed r1 · 2,862 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-code-oracle-filtered#Dataset package | Observed r1 · 15,165 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-agent-calendar#Dataset package | Observed r1 · 3,358 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-agent-workplace-v2#Dataset package | Observed r1 · 297 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-competitive-coding#Dataset package | Observed r1 · 15,713 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-identity-following-v2#Dataset package | Observed r1 · 21,660 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-instruction-following-adversarial-v3#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-instruction-following-calendar#Dataset package | Observed r1 · 8,387 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-instruction-following-structured#Dataset package | Observed r1 · 9,437 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-instruction-following-v2#Dataset package | Observed r1 · 46,391 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-knowledge-web-search-mcqa#Dataset package | Observed r1 · 2,915 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nemotron-gym-math-advanced-calculations-v3#Dataset package | Observed r1 · 5,291 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-nl2bash-tasks-cleaned-oracle#Dataset package | Observed r1 · 1,570 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-openswe-tasks-patched-v5-oracle-success#Dataset package | Observed r1 · 17,504 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-r2egym-patched-full-oracle#Dataset package | Observed r1 · 3,328 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-selfinstruct-naive-sandboxes-2-verified#Dataset package | Observed r1 · 9,638 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-swe-rebench-patched-oracle#Dataset package | Observed r1 · 3,787 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-swe-rebench-v2-patched-oracle#Dataset package | Observed r1 · 18,341 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-swegym-tasks-patched-validated-v2#Dataset package | Observed r1 · 989 registered tasks | Harbor Hub ↗ |
| openthoughts/tasktrove-swesmith-oracle-filtered#Dataset package | Observed r1 · 12,942 registered tasks | Harbor Hub ↗ |
| orca-bench/orca-bench#Dataset package | Observed r3 · 755 registered tasks | Harbor Hub ↗ |
| orca-bench/orca-bench-private#Dataset package | Observed r1 · 324 registered tasks | Harbor Hub ↗ |
| orca-bench/orca-bench-verified#Dataset package | Observed r1 · 40 registered tasks | Harbor Hub ↗ |
| orinlabs/horizon-1-public#Dataset package | Observed r1 · 3 registered tasks | Harbor Hub ↗ |
| orinlabs/horizon-public#Dataset package | Observed r3 · 3 registered tasks | Harbor Hub ↗ |
| pelican_svg_env#Environment manifest | envs/pelican_svg_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| PettingZoo#Foundation project | Upstream category: core | Farama Foundation ↗ |
| podcast-homepage#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| polyvorlabs/cyberdefense-bench#Dataset package | Observed r4 · 100 registered tasks | Harbor Hub ↗ |
| polyvorlabs/klyrune-bench#Dataset package | Observed r2 · 100 registered tasks | Harbor Hub ↗ |
| polyvorlabs/revbench#Dataset package | Observed r14 · 22 registered tasks | Harbor Hub ↗ |
| pomodoro#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| Procgen2#Foundation project | Upstream category: incubating | Farama Foundation ↗ |
| product-launch-page#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| punitarani/harvey-labs#Dataset package | Observed r1 · 1,760 registered tasks | Harbor Hub ↗ |
| qcircuitbench/qcircuitbench#Dataset package | Observed r1 · 28 registered tasks | Harbor Hub ↗ |
| qed_math_env#Environment manifest | envs/qed_math_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| qr-code-generator#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| quesma/compilebench#Dataset package | Observed r1 · 15 registered tasks | Harbor Hub ↗ |
| quesma/otel-bench#Dataset package | Observed r1 · 26 registered tasks | Harbor Hub ↗ |
| quixbugs/quixbugs#Dataset package | Observed r1 · 80 registered tasks | Harbor Hub ↗ |
| rachittshah/railhead#Dataset package | Observed r1 · 533 registered tasks | Harbor Hub ↗ |
| rachittshah/railhead-train#Dataset package | Observed r1 · 1,006 registered tasks | Harbor Hub ↗ |
| reactbench/reactbench#Dataset package | Observed r1 · 39 registered tasks | Harbor Hub ↗ |
| reasoning-gym/reasoning-gym-easy#Dataset package | Observed r1 · 288 registered tasks | Harbor Hub ↗ |
| reasoning-gym/reasoning-gym-hard#Dataset package | Observed r1 · 288 registered tasks | Harbor Hub ↗ |
| reasoning_gym_env#Environment manifest | envs/reasoning_gym_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| red-hat-ai/haiku-hard#Dataset package | Observed r4 · 138 registered tasks | Harbor Hub ↗ |
| red-hat-ai/SWE-benchify-hard#Dataset package | Observed r2 · 284 registered tasks | Harbor Hub ↗ |
| refresh/blenderbench-20#Dataset package | Observed r2 · 20 registered tasks | Harbor Hub ↗ |
| regex-lab#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| repl_env#Environment manifest | envs/repl_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| replicationbench/replicationbench#Dataset package | Observed r1 · 90 registered tasks | Harbor Hub ↗ |
| rexbench/rexbench#Dataset package | Observed r1 · 2 registered tasks | Harbor Hub ↗ |
| rounakbende10/rh-swe-bench#Dataset package | Observed r9 · 337 registered tasks | Harbor Hub ↗ |
| rsi-index/post-training#Dataset package | Observed r3 · 1 registered tasks | Harbor Hub ↗ |
| rsibench-infra/recursive-improve-cases#Dataset package | Observed r3 · 3 registered tasks | Harbor Hub ↗ |
| ryanmarten/tb-test#Dataset package | Observed r4 · 1 registered tasks | Harbor Hub ↗ |
| ryanmarten/tb4-preview#Dataset package | Observed r1 · 66 registered tasks | Harbor Hub ↗ |
| ryanmarten/terminal-bench-4-no-prebuild#Dataset package | Observed r1 · 66 registered tasks | Harbor Hub ↗ |
| satbench/satbench#Dataset package | Observed r1 · 2,100 registered tasks | Harbor Hub ↗ |
| scale-ai/hil-bench#Dataset package | Observed r5 · 600 registered tasks | Harbor Hub ↗ |
| scale-ai/hil-bench-sql-ask-human#Dataset package | Observed r2 · 100 registered tasks | Harbor Hub ↗ |
| scale-ai/hil-bench-swe-ask-human#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| scale-ai/swe-atlas-qna#Dataset package | Observed r1 · 124 registered tasks | Harbor Hub ↗ |
| scale-ai/swe-atlas-rf#Dataset package | Observed r1 · 70 registered tasks | Harbor Hub ↗ |
| scale-ai/swe-atlas-tw#Dataset package | Observed r2 · 90 registered tasks | Harbor Hub ↗ |
| scale-ai/swe-bench-pro#Dataset package | Observed r2 · 731 registered tasks | Harbor Hub ↗ |
| scienceagentbench/scienceagentbench#Dataset package | Observed r1 · 102 registered tasks | Harbor Hub ↗ |
| Shimmy#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| shiv-eshwar/lb6-dev-pilot-issue18-rewardkit#Dataset package | Observed r4 · 12 registered tasks | Harbor Hub ↗ |
| sierra-research/tau3-bench#Dataset package | Observed r1 · 375 registered tasks | Harbor Hub ↗ |
| silrlab/long-horizon-terminal-bench#Dataset package | Observed r3 · 46 registered tasks | Harbor Hub ↗ |
| silrlab/long-horizon-terminal-bench-2.0#Dataset package | Observed r2 · 77 registered tasks | Harbor Hub ↗ |
| silverwhite/slopcodebench-friction#Dataset package | Observed r1 · 36 registered tasks | Harbor Hub ↗ |
| skill2env/skill2env#Dataset package | Observed r2 · 7,496 registered tasks | Harbor Hub ↗ |
| sldbench/sldbench#Dataset package | Observed r1 · 8 registered tasks | Harbor Hub ↗ |
| snake_env#Environment manifest | envs/snake_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| snorkel-ai/senior-swe-bench-v2026.06#Dataset package | Observed r5 · 50 registered tasks | Harbor Hub ↗ |
| snowflake-labs/data-eng-bench#Dataset package | Observed r1 · 103 registered tasks | Harbor Hub ↗ |
| solar-system-explorer#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| solar-system-explorer-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| sophistry_bench_sprint_env#Environment manifest | envs/sophistry_bench_sprint_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| Stable-Retro#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| stanford/medagentbench#Dataset package | Observed r1 · 300 registered tasks | Harbor Hub ↗ |
| strongreject/strongreject#Dataset package | Observed r1 · 150 registered tasks | Harbor Hub ↗ |
| sumo_rl_env#Environment manifest | envs/sumo_rl_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| svgap/svgap-reset-release#Dataset package | Observed r4 · 8 registered tasks | Harbor Hub ↗ |
| swe-bench/swe-bench-verified#Dataset package | Observed r2 · 500 registered tasks | Harbor Hub ↗ |
| swe-bench/swe-smith#Dataset package | Observed r1 · 100 registered tasks | Harbor Hub ↗ |
| swe-rebench/swe-rebench-leaderboard#Dataset package | Observed r2 · 860 registered tasks | Harbor Hub ↗ |
| swt-bench/swt-bench-verified#Dataset package | Observed r1 · 433 registered tasks | Harbor Hub ↗ |
| synthetic-sciences/frontierml#Dataset package | Observed r1 · 0 registered tasks | Harbor Hub ↗ |
| target-clicker#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| tau2_env#Environment manifest | envs/tau2_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| tbench-dw-a-dw_1784073139_2608908/dw-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-dw2-a-dw2_1784073189_2619080/dw2-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-dw3-a-dw3_1784073253_2627946/dw3-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-lbtest-a-xt_1784071893_2521724/xt-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-lbtest-lb_1784071796_2517183/lbtest-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-pubcrack-a-pc_1784073251/pubcrack-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-rv-a-rv_1784073719_2926154/rv-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-up-a-up_1784106749_3678887/up-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-up2-a-up2_1784107856_4005736/up2-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-up3-a-up3_1784108188_141385/up3-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench-up4-a-up4_1784108341_146593/up4-dataset#Dataset package | No visible latest-version metadata | Harbor Hub ↗ |
| tbench2_env#Environment manifest | envs/tbench2_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| tea-drunkability-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| tea-dunkability#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| tencent/autocodebench#Dataset package | Observed r1 · 200 registered tasks | Harbor Hub ↗ |
| termigen/termigen-environments#Dataset package | Observed r1 · 3,566 registered tasks | Harbor Hub ↗ |
| terminal-bench-pro/terminal-bench-pro#Dataset package | Observed r1 · 200 registered tasks | Harbor Hub ↗ |
| terminal-bench-science/terminal-bench-science#Dataset package | Observed r10 · 70 registered tasks | Harbor Hub ↗ |
| terminal-bench/terminal-bench#Dataset package | Observed r4 · 66 registered tasks | Harbor Hub ↗ |
| terminal-bench/terminal-bench-2#Dataset package | Observed r1 · 89 registered tasks | Harbor Hub ↗ |
| terminal-bench/terminal-bench-2-1#Dataset package | Observed r6 · 89 registered tasks | Harbor Hub ↗ |
| terminal-bench/terminal-bench-cpu-only#Dataset package | Observed r1 · 63 registered tasks | Harbor Hub ↗ |
| terminus_env#Environment manifest | envs/terminus_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| textarena_env#Environment manifest | envs/textarena_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| theagentcompany/theagentcompany#Dataset package | Observed r3 · 174 registered tasks | Harbor Hub ↗ |
| thetalab/vector-edit-gym#Dataset package | Observed r1 · 106 registered tasks | Harbor Hub ↗ |
| thinkingbox_env#Environment manifest | envs/thinkingbox_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| tic-tac-toe-game#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| timewarp#Benchmark configuration | Configuration: timewarp | BrowserGym ↗ |
| tiny-kanban#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| tinycomputerai/bun-server-bench#Dataset package | Observed r4 · 50 registered tasks | Harbor Hub ↗ |
| titouanlne/arc-agi-2-k8s#Dataset package | Observed r1 · 167 registered tasks | Harbor Hub ↗ |
| titouanlne/dbt-labs-k8s#Dataset package | Observed r2 · 48 registered tasks | Harbor Hub ↗ |
| tmax/TMax-15K-Harbor#Dataset package | Observed r2 · 14,601 registered tasks | Harbor Hub ↗ |
| tmax/TMax-15K-Harbor-trial#Dataset package | Observed r1 · 12 registered tasks | Harbor Hub ↗ |
| tomseimandi/ade-bench#Dataset package | Observed r1 · 48 registered tasks | Harbor Hub ↗ |
| trivia-quiz-game#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| typing-rain#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| typing-rain-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| unity_env#Environment manifest | envs/unity_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| usaco/usaco#Dataset package | Observed r1 · 304 registered tasks | Harbor Hub ↗ |
| userbench/UserBench#Dataset package | Observed r7 · 620 registered tasks | Harbor Hub ↗ |
| userbench/UserBench-train400#Dataset package | Observed r4 · 620 registered tasks | Harbor Hub ↗ |
| vals/financeagent#Dataset package | Observed r1 · 50 registered tasks | Harbor Hub ↗ |
| vibrantlabsai/itsm-bench#Dataset package | Observed r5 · 53 registered tasks | Harbor Hub ↗ |
| viratzzs/petct-pilot#Dataset package | Observed r3 · 2 registered tasks | Harbor Hub ↗ |
| virtual-drum-kit#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| virtual-drum-kit-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| visualwebarena#Benchmark configuration | Configuration: visualwebarena | BrowserGym ↗ |
| visualwebarena_tiny#Benchmark configuration | Configuration: visualwebarena_tiny | BrowserGym ↗ |
| ViZDoom#Foundation project | Upstream category: mature | Farama Foundation ↗ |
| vmax-modal/modal-port-v1-eval-patched#Dataset package | Observed r1 · 427 registered tasks | Harbor Hub ↗ |
| vmax-modal/modal-port-v1-train-patched#Dataset package | Observed r2 · 1,702 registered tasks | Harbor Hub ↗ |
| vmax/vmax-tasks#Dataset package | Observed r1 · 1,043 registered tasks | Harbor Hub ↗ |
| weather-theatre#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| weather-theatre-5.2#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| webarena#Benchmark configuration | Configuration: webarena | BrowserGym ↗ |
| webarena_lite#Benchmark configuration | Configuration: webarena_lite | BrowserGym ↗ |
| webarena_tiny#Benchmark configuration | Configuration: webarena_tiny | BrowserGym ↗ |
| webarena_verified#Benchmark configuration | Configuration: webarena_verified | BrowserGym ↗ |
| webcam-filter-playground#Coding example manifest | Matching application source present View manifest ↗ | OpenAI coding examples ↗ |
| webgen-bench/webgen-bench#Dataset package | Observed r3 · 101 registered tasks | Harbor Hub ↗ |
| weblinx#Benchmark configuration | Configuration: weblinx | BrowserGym ↗ |
| websearch_env#Environment manifest | envs/websearch_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| wildfire_env#Environment manifest | envs/wildfire_env/openenv.yaml View manifest ↗ | OpenEnv ↗ |
| withmartian/clojure-swerebench-v2-validated-51#Dataset package | Observed r1 · 51 registered tasks | Harbor Hub ↗ |
| workarena_l1#Benchmark configuration | Configuration: workarena_l1 | BrowserGym ↗ |
| workarena_l2_agent_curriculum_eval#Benchmark configuration | Configuration: workarena_l2_agent_curriculum_eval | BrowserGym ↗ |
| workarena_l3_agent_curriculum_eval#Benchmark configuration | Configuration: workarena_l3_agent_curriculum_eval | BrowserGym ↗ |
| xiaoboai/pawbench#Dataset package | Observed r1 · 150 registered tasks | Harbor Hub ↗ |
| xlang-ai/osworld-verified#Dataset package | Observed r1 · 361 registered tasks | Harbor Hub ↗ |
| xlang/ds-1000#Dataset package | Observed r1 · 1,000 registered tasks | Harbor Hub ↗ |
| yanagiorigami/frontier-cs#Dataset package | Observed r1 · 172 registered tasks | Harbor Hub ↗ |
| ykhli/tetrisbench#Dataset package | Observed r1 · 1 registered tasks | Harbor Hub ↗ |
| zenml/zenml-bench#Dataset package | Observed r1 · 18 registered tasks | Harbor Hub ↗ |
No matching records.
Change your search or reset the filters.
Sources and coverage
Captures retain response hashes and source references. Public package visibility does not establish permissive licensing or immediate runtime availability; inspect the upstream requirements. Source configuration JSON ↗
Harbor Hub
Public dataset packages, including community forks, experiments and non-software tasks. A latest tag is mutable; recorded revisions and hashes identify the observed version. Missing version metadata is retained. Package counts are not distinct benchmark counts.
This capture contains 355 public packages and 344 latest-tag records; 11 packages lack visible version metadata.
The framework license does not grant rights to every registered dataset or task. Follow the package's own source and terms.
Query client code revision: 2de4605b9404eada7d341388291e6e469c90330b · 2026-10-16
Captured: 2026-10-16T12:10:39.035948+00:00
OpenEnv
Tracked environment manifests at the pinned repository revision. These include wrappers and examples; the inventory excludes external community repositories and hosted deployments. A manifest does not establish runtime availability.
OpenEnv's BSD license does not replace wrapped environments' and dependencies' individual terms.
Pinned repository revision: 55347f62e22f83a618b49ee984e2f684b69d8fbd · 2026-10-15
Captured: 2026-10-16T12:10:29.891055+00:00
BrowserGym
Named configurations extracted from source without importing it. Tiny, lite and curriculum variants remain configurations, not additional independent projects. A wrapper can also target a static dataset.
BrowserGym code is Apache 2.0; underlying benchmarks have separate access, setup and licensing requirements.
Pinned repository revision: e71419aef5759a11cb7896a26c36e5f7e92d82b2 · 2026-10-05
Captured: 2026-10-16T12:10:29.022024+00:00
Farama Foundation
The foundation's project catalog, including environments, libraries and offline-data infrastructure. Core, mature and incubating are upstream governance labels. This is not a census of all reinforcement-learning environments.
Only factual names, URLs and upstream category labels are retained. Project code, data and assets retain their own licenses.
Captured: 2026-10-16T12:10:29.731162+00:00
OpenAI coding examples
Published example manifests at a dated repository revision. Model variants may repeat a project idea. Matching application source is recorded when present; manifest discovery is not application testing or independent verification of generation history.
The repository's MIT code license does not establish the rights of every linked external asset or dependency. Prompt bodies and screenshots are not republished here.
Pinned repository revision: 77f6322723703941f0b884d1a1cb77c60aad5187 · 2025-12-11
Captured: 2026-10-16T12:10:30.460708+00:00