# Stake

Source: [Stake](<https://www.sota2.com/research/task/stake>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.



## Benchmarks

Page 1 of 1. This is an index page, not the full collection.

- [High-stakes specialized classification on ChemProt (test)](<https://www.sota2.com/research/sota/high-stakes-specialized-classification-on-chemprot-test.md>): High-stakes specialized classification; ChemProt (test).

- [High-stakes specialized classification on Claude9 (test)](<https://www.sota2.com/research/sota/high-stakes-specialized-classification-on-claude9-test.md>): High-stakes specialized classification; Claude9 (test).

- [High-stakes specialized classification on DDI (test)](<https://www.sota2.com/research/sota/high-stakes-specialized-classification-on-ddi-test.md>): High-stakes specialized classification; DDI (test).

- [Math Mistake Remediation on Math Mistake Remediation Dataset](<https://www.sota2.com/research/sota/math-mistake-remediation-on-math-mistake-remediation-dataset.md>): Math Mistake Remediation; Math Mistake Remediation Dataset.

- [Procedural mistake detection on Assembly101-O](<https://www.sota2.com/research/sota/procedural-mistake-detection-on-assembly101-o.md>): Procedural mistake detection; Assembly101-O.

- [Mistake Detection on HoloAssist (test)](<https://www.sota2.com/research/sota/mistake-detection-on-holoassist-test.md>): Mistake Detection; HoloAssist (test).

- [Procedural Mistake Detection on Epic-tent-O](<https://www.sota2.com/research/sota/procedural-mistake-detection-on-epic-tent-o.md>): Procedural mistake detection; Epic-tent-O.

- [Adding Mistake on FOLIO](<https://www.sota2.com/research/sota/adding-mistake-on-folio.md>): Adding Mistake; FOLIO.

- [Adding Mistake on MuSR](<https://www.sota2.com/research/sota/adding-mistake-on-musr.md>): Adding Mistake; MuSR.

- [Adding Mistake on ZebraLogicBench (ZLB)](<https://www.sota2.com/research/sota/adding-mistake-on-zebralogicbench-zlb.md>): Adding Mistake; ZebraLogicBench (ZLB).

- [Adding Mistake on BBEH](<https://www.sota2.com/research/sota/adding-mistake-on-bbeh.md>): Adding Mistake; BBEH.

- [Mistake Correction on BIG-Bench Mistake (BBM)](<https://www.sota2.com/research/sota/mistake-correction-on-big-bench-mistake-bbm.md>): Mistake Correction; BIG-Bench Mistake (BBM).

- [Segment-level mistake detection on EgoPER](<https://www.sota2.com/research/sota/segment-level-mistake-detection-on-egoper.md>): Segment-level mistake detection; EgoPER.

- [Factual mistake detection on DocENT (PoSh)](<https://www.sota2.com/research/sota/factual-mistake-detection-on-docent-posh.md>): Factual mistake detection; DocENT (PoSh).

- [Multi-Stakeholder Recommendation on Steam Games](<https://www.sota2.com/research/sota/multi-stakeholder-recommendation-on-steam-games.md>): Multi-Stakeholder Recommendation; Steam Games.

- [Multi-Stakeholder Recommendation on Goodreads YA](<https://www.sota2.com/research/sota/multi-stakeholder-recommendation-on-goodreads-ya.md>): Multi-Stakeholder Recommendation; Goodreads YA.

- [Multi-Stakeholder Recommendation on Movies & TV](<https://www.sota2.com/research/sota/multi-stakeholder-recommendation-on-movies-and-tv.md>): Multi-Stakeholder Recommendation; Movies & TV.

- [Multi-Stakeholder Recommendation on CDs & Vinyl](<https://www.sota2.com/research/sota/multi-stakeholder-recommendation-on-cds-and-vinyl.md>): Multi-Stakeholder Recommendation; CDs & Vinyl.

- [Segment-level mistake detection on CaptainCook4D (Average)](<https://www.sota2.com/research/sota/segment-level-mistake-detection-on-captaincook4d-average.md>): Segment-level mistake detection; CaptainCook4D (Average).

- [Mistake detection on Multi-robot dataset Ordering (test)](<https://www.sota2.com/research/sota/mistake-detection-on-multi-robot-dataset-ordering-test.md>): Mistake detection; Multi-robot dataset Ordering (test).

- [Mistake detection on Multi-robot dataset Mutex (test)](<https://www.sota2.com/research/sota/mistake-detection-on-multi-robot-dataset-mutex-test.md>): Mistake detection; Multi-robot dataset Mutex (test).

- [Mistake detection on BridgeData V2 (test)](<https://www.sota2.com/research/sota/mistake-detection-on-bridgedata-v2-test.md>): Mistake detection; BridgeData V2 (test).

- [Mistake Detection on HoloAssist](<https://www.sota2.com/research/sota/mistake-detection-on-holoassist.md>): Mistake Detection; HoloAssist.

- [Segment-level mistake detection on CaptainCook4D 5-recipe average](<https://www.sota2.com/research/sota/segment-level-mistake-detection-on-captaincook4d-5-recipe-average.md>): Segment-level mistake detection; CaptainCook4D 5-recipe average.

- [Task-level mistake detection on EgoPER](<https://www.sota2.com/research/sota/task-level-mistake-detection-on-egoper.md>): Task-level mistake detection; EgoPER.

- [High-stakes specialized classification on Claude9 (val)](<https://www.sota2.com/research/sota/high-stakes-specialized-classification-on-claude9-val.md>): High-stakes specialized classification; Claude9 (val).

- [High-stakes specialized classification on DDI (val)](<https://www.sota2.com/research/sota/high-stakes-specialized-classification-on-ddi-val.md>): High-stakes specialized classification; DDI (val).

- [High-stakes specialized classification on ChemProt (val)](<https://www.sota2.com/research/sota/high-stakes-specialized-classification-on-chemprot-val.md>): High-stakes specialized classification; ChemProt (val).

- [Mistake Detection on EgoPER](<https://www.sota2.com/research/sota/mistake-detection-on-egoper.md>): Mistake Detection; EgoPER.

- [Mistake Detection on Ego4D-M (test)](<https://www.sota2.com/research/sota/mistake-detection-on-ego4d-m-test.md>): Mistake Detection; Ego4D-M (test).

- [Mistake Detection on EPIC-KITCHENS-M (EK) (test)](<https://www.sota2.com/research/sota/mistake-detection-on-epic-kitchens-m-ek-test.md>): Mistake Detection; EPIC-KITCHENS-M (EK) (test).

- [Early mistake detection on Captain-Cook4D and Assembly101 (test)](<https://www.sota2.com/research/sota/early-mistake-detection-on-captain-cook4d-and-assembly101-test.md>): Early mistake detection; Captain-Cook4D and Assembly101 (test).

- [Stake on Dataset 3](<https://www.sota2.com/research/sota/stake-on-dataset-3.md>): Stake; Dataset 3.