{"schema_version":"0.1","id":"33dc9d9b-5190-4ba7-b405-975f21b5c08e","display_name":"Jana Nováková","handle":"jana-novak","avatar_url":null,"positioning":"PhD student. Reproduces other people's benchmark claims.","topics":["Reproducibility","Evaluation"],"region":"Prague, Czechia","languages":{"content":["English","Czech"],"communication":["English","Czech"]},"time_zone":"Europe/Prague","accounts":[{"platform":"github","handle":"jana-novak","url":null,"ownership_status":"verified","metric_snapshot":{"metric":"followers","value":430,"unit":null,"period":null,"sample_size":null,"as_of":"2026-11-03T07:05:30.284Z","source_type":"platform_api","historical":false},"evidence":[{"type":"account_connected","label":"Account connected","scope":"The creator signed in with this account.","does_not_establish":"Does not establish audience quality.","review_status":"passed","version":null,"date":"2026-09-02T06:05:30.284Z"}]}],"works":[{"id":"25f32a06-73db-4574-81d2-c91703f69c0f","type":"article","title":"I re-ran 12 viral benchmark posts. Here's what held up.","role":null,"personal_contribution":null,"outcome":null,"limitations":null,"version":null,"links":[],"disclosure":"independent","pinned":true,"run_id":null,"evidence":[{"type":"reproduced","label":"Independently reproduced","scope":"Another member re-ran it and matched the reported results.","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":null,"date":"2026-10-26T13:05:30.284Z"}],"updated_at":"2026-10-26T13:05:30.284Z","date":"2026-10-26","visibility":"public"},{"id":"b5721972-6448-481d-823b-6883337ab922","type":"run","title":"Llama-3.1-8B-Instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on llama3.1:8b-instruct-q4_K_M, Apple M1 Max · 64 GB.","outcome":"code-intervals 1/3 · tool-flight 3/3 · needle-8k 3/3 · 52.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"8d90dfee-4701-4461-81a5-4bc82a9a3803","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-11-04T15:11:25.182Z"}],"updated_at":"2026-11-04T15:11:25.182Z","date":"2026-11-04","visibility":"public"},{"id":"cbebc1ef-08d4-4ded-a538-d9bcbff017aa","type":"run","title":"gemma-3-12b-it on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for gemma3:12b-it-q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 3/3 · tool-flight not supported · needle-8k 2/3 · 81.7 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"1ffb95ef-45ba-48e1-9165-779d01c5554d","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 2 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-11-02T18:10:10.966Z"}],"updated_at":"2026-11-02T18:10:10.966Z","date":"2026-11-02","visibility":"public"},{"id":"574a0cb7-1bb5-4a13-a6f8-2b8b432619dc","type":"run","title":"Phi-3.5-mini-instruct on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on phi3.5:3.8b-mini-instruct-q4_K_M, Apple M1 Max · 64 GB.","outcome":"code-intervals 1/3 · tool-flight not supported · needle-8k 3/3 · 112.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"aec16ba2-c1f4-4626-8ec8-3e23334c9118","evidence":[{"type":"verified","label":"Verified","scope":"1 of 2 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-28T12:33:26.741Z"}],"updated_at":"2026-10-28T12:33:26.741Z","date":"2026-10-28","visibility":"public"},{"id":"ce524ae0-838b-45bf-9938-090f8eaa74ce","type":"run","title":"GLM-4.7-Flash on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for glm-4.7-flash:q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 201.7 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"f62b5c31-04ae-418a-8913-4b21b6106157","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 3 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-24T01:47:27.653Z"}],"updated_at":"2026-10-24T01:47:27.653Z","date":"2026-10-24","visibility":"public"},{"id":"5a56113b-c2d9-4dfd-9d00-7a839deb7b83","type":"run","title":"Qwen3-14B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:14b-q4_K_M, Apple M1 Max · 64 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 28.2 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"c8c09614-2ce0-477f-b5fd-93129c004f9e","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-20T18:48:26.092Z"}],"updated_at":"2026-10-20T18:48:26.092Z","date":"2026-10-20","visibility":"public"},{"id":"7fb39a44-4783-4c49-9ca3-9c81ee55f940","type":"run","title":"gpt-oss-20b on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gpt-oss:20b, Apple M1 Max · 64 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 68.3 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · MXFP4","links":[],"disclosure":"not_stated","pinned":false,"run_id":"22a5353d-e064-4da1-9646-dfd1049f0236","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · MXFP4","date":"2026-10-13T22:59:07.036Z"}],"updated_at":"2026-10-13T22:59:07.036Z","date":"2026-10-13","visibility":"public"},{"id":"d47c21eb-e95e-4dbd-9b36-d823e0703627","type":"run","title":"Qwen3.5-2B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3.5:2b-q4_K_M, Apple M1 Max · 64 GB.","outcome":"code-intervals 3/3 · tool-flight 2/3 · needle-8k 3/3 · 132.0 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"e1da8a6c-8831-45dc-838f-96cd23f2954e","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-10-06T18:26:15.373Z"}],"updated_at":"2026-10-06T18:26:15.373Z","date":"2026-10-06","visibility":"public"},{"id":"08e80da6-353e-4c77-9314-59de2999708f","type":"run","title":"gpt-oss-20b on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for gpt-oss:20b on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 1/3 · 173.8 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · MXFP4","links":[],"disclosure":"not_stated","pinned":false,"run_id":"ae461321-ef13-433a-9e45-2ab6feb5e8c0","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 3 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · MXFP4","date":"2026-10-06T00:28:57.861Z"}],"updated_at":"2026-10-06T00:28:57.861Z","date":"2026-10-06","visibility":"public"},{"id":"6a52a661-5e46-41ae-b8b1-32186ffc17aa","type":"run","title":"gpt-oss-20b on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gpt-oss:20b, Apple M1 Max · 64 GB.","outcome":"code-intervals 3/3 · tool-flight 2/3 · needle-8k 3/3 · 69.1 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · MXFP4","links":[],"disclosure":"not_stated","pinned":false,"run_id":"46315c84-512f-4b8a-80d3-ec39d67c2cb3","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · MXFP4","date":"2026-09-29T15:33:28.753Z"}],"updated_at":"2026-09-29T15:33:28.753Z","date":"2026-09-29","visibility":"public"},{"id":"fe823c6a-a7ab-487e-b85b-742330a3c698","type":"run","title":"gemma-3-12b-it on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Queued suite-standard@1.0 for gemma3:12b-it-q4_K_M on BenchClub cloud, NVIDIA L40S · 48 GB, pinned environment.","outcome":"code-intervals 2/3 · tool-flight not supported · needle-8k 3/3 · 81.9 tok/s decode at speed@0","limitations":"Applies to this build and suite version on BenchClub's pinned cloud environment. Counts toward headline results.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"36b7a664-9938-409f-bab1-56c6d5163b6a","evidence":[{"type":"verified","label":"Verified","scope":"Run on BenchClub cloud; all 2 tasks graded by the platform","does_not_establish":"Does not establish results on other hardware.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-29T01:07:09.874Z"}],"updated_at":"2026-09-29T01:07:09.874Z","date":"2026-09-29","visibility":"public"},{"id":"a0e181fc-efad-45da-b2f5-1b11b3c1abf8","type":"run","title":"Qwen3-8B on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on qwen3:8b-q4_K_M, Apple M1 Max · 64 GB.","outcome":"code-intervals 2/3 · tool-flight 3/3 · needle-8k 3/3 · 50.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · Q4_K_M","links":[],"disclosure":"not_stated","pinned":false,"run_id":"362834fa-eec1-43e8-a888-d19edee23c36","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · Q4_K_M","date":"2026-09-23T16:40:07.862Z"}],"updated_at":"2026-09-23T16:40:07.862Z","date":"2026-09-23","visibility":"public"},{"id":"a4bd43e6-be7a-4b76-b7c7-7c5542288fbe","type":"run","title":"gpt-oss-20b on suite-standard@1.0","role":"Ran the suite","personal_contribution":"Ran suite-standard@1.0 on gpt-oss:20b, Apple M1 Max · 64 GB.","outcome":"code-intervals 3/3 · tool-flight 3/3 · needle-8k 3/3 · 68.4 tok/s decode at speed@0","limitations":"Applies to this build, machine and suite version. A single community run on the submitter's machine, not part of headline numbers.","version":"suite-standard@1.0 · MXFP4","links":[],"disclosure":"not_stated","pinned":false,"run_id":"28238c86-7e8e-4376-bbb1-69572822115f","evidence":[{"type":"verified","label":"Verified","scope":"2 of 3 tasks regraded from the event log; code tasks not regraded","does_not_establish":"Does not establish reliability on other machines or that the platform executed the run.","review_status":"passed","version":"suite-standard@1.0 · MXFP4","date":"2026-09-16T13:03:23.015Z"}],"updated_at":"2026-09-16T13:03:23.015Z","date":"2026-09-16","visibility":"public"}],"collaboration":{"formats":["Advisory"],"availability":null},"reputation":{"verified_works":13,"reproductions":1,"tier":"regular"},"updated_at":"2026-11-03T07:05:30.284Z"}