# EDA on Things-30 EDA (subsampled) Source: [EDA on Things-30 EDA (subsampled)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:44.805Z Evaluation of EDA performance on the subsampled test set of the Things-30 dataset, reporting metrics such as Turns, Success rate, and Score. 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. | Scope | Recorded value | | --- | --- | | Task | EDA | | Dataset (including any stated split) | Things-30 EDA (subsampled) | | Metric | Turns | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 27 of 27 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Turns](): Higher is better; unit: SCALAR. - [Success Rate](): Higher is better; unit: PERCENT. - [Yes Count](): Higher is better; unit: SCALAR. - [Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Turns | Result date | Report paper | | --- | --- | --- | --- | | V-FT | 19.7 | Not recorded | 68fa72471e209131cea55847 | | Vicuna 7B | 19.5 | Not recorded | 68fa72471e209131cea55847 | | V-RLGP | 19.3 | Not recorded | 68fa72471e209131cea55847 | | V-FT 7B (All) | 19.2 | Not recorded | 68fa72471e209131cea55847 | | Vicuna | 19.1 | Not recorded | 68fa72471e209131cea55847 | | Mistral 7B | 18.9 | Not recorded | 68fa72471e209131cea55847 | | Claude-1 | 18.8 | Not recorded | 68fa72471e209131cea55847 | | Claude-1 | 18.7 | Not recorded | 68fa72471e209131cea55847 | | Vicuna | 18.7 | Not recorded | 68fa72471e209131cea55847 | | V-FT 13B (All) | 18.6 | Not recorded | 68fa72471e209131cea55847 | | V-FT | 18.5 | Not recorded | 68fa72471e209131cea55847 | | V-FT | 18.5 | Not recorded | 68fa72471e209131cea55847 | | Human | 18.5 | Not recorded | 68fa72471e209131cea55847 | | GPT-3.5 | 18.4 | Not recorded | 68fa72471e209131cea55847 | | V-FT | 18.4 | Not recorded | 68fa72471e209131cea55847 | | Claude-2 | 18.4 | Not recorded | 68fa72471e209131cea55847 | | Vicuna 13B | 18.4 | Not recorded | 68fa72471e209131cea55847 | | GPT-3.5 | 18.2 | Not recorded | 68fa72471e209131cea55847 | | V-FT | 18 | Not recorded | 68fa72471e209131cea55847 | | V-FT 7B (Suc.) | 18 | Not recorded | 68fa72471e209131cea55847 | | V-FT 13B (Suc.) | 18 | Not recorded | 68fa72471e209131cea55847 | | V-RLGP 13B | 17.9 | Not recorded | 68fa72471e209131cea55847 | | V-RLGP | 17.8 | Not recorded | 68fa72471e209131cea55847 | | GPT-4 | 17.8 | Not recorded | 68fa72471e209131cea55847 | | V-RLGP 7B | 17.8 | Not recorded | 68fa72471e209131cea55847 | | Claude-2 | 17.6 | Not recorded | 68fa72471e209131cea55847 | | GPT-4 | 16.9 | Not recorded | 68fa72471e209131cea55847 | ### V-FT Turns: 19.7. Result ID: 69922ac13a6c3148490d08c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Vicuna 7B","Training Data":"Celebs"}. This record does not assert independent reproduction. ### Vicuna 7B Turns: 19.5. Result ID: 69922ac13a6c3148490d08db. [Reporting paper]() Recorded evaluation configuration: {"Size":"7B","Version":"v1.3"}. This record does not assert independent reproduction. ### V-RLGP Turns: 19.3. Result ID: 69922ac13a6c3148490d08c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Vicuna 7B"}. This record does not assert independent reproduction. ### V-FT 7B (All) Turns: 19.2. Result ID: 69922ac13a6c3148490d08dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Training Data":"All turns"}. This record does not assert independent reproduction. ### Vicuna Turns: 19.1. Result ID: 69922ac13a6c3148490d08bf. [Reporting paper]() Recorded evaluation configuration: {"Model size":"7B"}. This record does not assert independent reproduction. ### Mistral 7B Turns: 18.9. Result ID: 69922ac13a6c3148490d08dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Claude-1 Turns: 18.8. Result ID: 69922ac13a6c3148490d08d9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude-1 Turns: 18.7. Result ID: 69922ac13a6c3148490d08bd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Vicuna Turns: 18.7. Result ID: 69922ac13a6c3148490d08be. [Reporting paper]() Recorded evaluation configuration: {"Model size":"13B"}. This record does not assert independent reproduction. ### V-FT 13B (All) Turns: 18.6. Result ID: 69922ac13a6c3148490d08df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"13B","Training Data":"All turns"}. This record does not assert independent reproduction. ### V-FT Turns: 18.5. Result ID: 69922ac13a6c3148490d08c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Vicuna 7B","Training Data":"Things"}. This record does not assert independent reproduction. ### V-FT Turns: 18.5. Result ID: 69922ac13a6c3148490d08c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Vicuna 7B","Training Data":"Success trajectories"}. This record does not assert independent reproduction. ### Human Turns: 18.5. Result ID: 69922ac13a6c3148490d08c7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-3.5 Turns: 18.4. Result ID: 69922ac13a6c3148490d08bb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### V-FT Turns: 18.4. Result ID: 69922ac13a6c3148490d08c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Vicuna 7B","Training Data":"All"}. This record does not assert independent reproduction. ### Claude-2 Turns: 18.4. Result ID: 69922ac13a6c3148490d08d8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Vicuna 13B Turns: 18.4. Result ID: 69922ac13a6c3148490d08da. [Reporting paper]() Recorded evaluation configuration: {"Size":"13B","Version":"v1.3"}. This record does not assert independent reproduction. ### GPT-3.5 Turns: 18.2. Result ID: 69922ac13a6c3148490d08d7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### V-FT Turns: 18. Result ID: 69922ac13a6c3148490d08c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Vicuna 13B","Training Data":"Success trajectories"}. This record does not assert independent reproduction. ### V-FT 7B (Suc.) Turns: 18. Result ID: 69922ac13a6c3148490d08de. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Training Data":"Successful turns only"}. This record does not assert independent reproduction. ### V-FT 13B (Suc.) Turns: 18. Result ID: 69922ac13a6c3148490d08e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"13B","Training Data":"Successful turns only"}. This record does not assert independent reproduction. ### V-RLGP 13B Turns: 17.9. Result ID: 69922ac13a6c3148490d08e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"13B"}. This record does not assert independent reproduction. ### V-RLGP Turns: 17.8. Result ID: 69922ac13a6c3148490d08c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Vicuna 13B"}. This record does not assert independent reproduction. ### GPT-4 Turns: 17.8. Result ID: 69922ac13a6c3148490d08d6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### V-RLGP 7B Turns: 17.8. Result ID: 69922ac13a6c3148490d08e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Claude-2 Turns: 17.6. Result ID: 69922ac13a6c3148490d08bc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4 Turns: 16.9. Result ID: 69922ac13a6c3148490d08ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.