# Comprehensive Data Intelligence on Aggregated Benchmarks (DABench, DSBench, TableBench, DABStep-R) Source: [Comprehensive Data Intelligence on Aggregated Benchmarks (DABench, DSBench, TableBench, DABStep-R)]() Collection index: [llms.txt]() Data updated: 2026-06-16T10:25:20.995Z Performance evaluation across the combined suite of DABench, DSBench, TableBench, and DABStep-R, focusing on comprehensive data intelligence capabilities, measured by Overall and GR scores. 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 | Comprehensive Data Intelligence | | Dataset (including any stated split) | Aggregated Benchmarks (DABench, DSBench, TableBench, DABStep-R) | | Metric | Overall Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Overall Score](): Higher is better; unit: PERCENT. - [GR Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Score | Result date | Report paper | | --- | --- | --- | --- | | VeriGraph-8B | 73.68 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Claude-4.5-Opus | 73.22 | Not recorded | 6a30d8e4d33dfb23e783d025 | | GPT-5.4 | 72.01 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Claude-4.5-Sonnet | 71.17 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Qwen3-32B | 70.98 | Not recorded | 6a30d8e4d33dfb23e783d025 | | DeepAnalyze | 66.54 | Not recorded | 6a30d8e4d33dfb23e783d025 | | GPT-5.2 | 64.98 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Qwen3-30B-A3B | 64.36 | Not recorded | 6a30d8e4d33dfb23e783d025 | | QwQ-32B | 63.43 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Qwen3-8B | 62.35 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Claude-4.5-Opus | 58.85 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Claude-4.5-Sonnet | 56.27 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Gemini-2.5-Pro | 55.86 | Not recorded | 6a30d8e4d33dfb23e783d025 | | DataMind | 55.06 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Qwen3-32B | 53.8 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Qwen3-30B-A3B | 53.18 | Not recorded | 6a30d8e4d33dfb23e783d025 | | Qwen3-Coder-30B | 51.25 | Not recorded | 6a30d8e4d33dfb23e783d025 | | GPT-5.2 | 48.75 | Not recorded | 6a30d8e4d33dfb23e783d025 | ### VeriGraph-8B Overall Score: 73.68. Result ID: 6a31247bfbc373592c2e3379. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Specialized data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✓"}. This record does not assert independent reproduction. ### Claude-4.5-Opus Overall Score: 73.22. Result ID: 6a31247bfbc373592c2e3371. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### GPT-5.4 Overall Score: 72.01. Result ID: 6a31247bfbc373592c2e336f. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet Overall Score: 71.17. Result ID: 6a31247bfbc373592c2e3370. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Qwen3-32B Overall Score: 70.98. Result ID: 6a31247bfbc373592c2e3375. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### DeepAnalyze Overall Score: 66.54. Result ID: 6a31247bfbc373592c2e3378. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Specialized data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### GPT-5.2 Overall Score: 64.98. Result ID: 6a31247bfbc373592c2e336e. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B Overall Score: 64.36. Result ID: 6a31247bfbc373592c2e3376. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### QwQ-32B Overall Score: 63.43. Result ID: 6a31247bfbc373592c2e3374. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Qwen3-8B Overall Score: 62.35. Result ID: 6a31247bfbc373592c2e3372. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Claude-4.5-Opus Overall Score: 58.85. Result ID: 6a31247bfbc373592c2e336b. [Reporting paper]() Recorded evaluation configuration: {"Category":"Direct inference","Traceability (Comp.)":"✗","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet Overall Score: 56.27. Result ID: 6a31247bfbc373592c2e336a. [Reporting paper]() Recorded evaluation configuration: {"Category":"Direct inference","Traceability (Comp.)":"✗","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Overall Score: 55.86. Result ID: 6a31247bfbc373592c2e3369. [Reporting paper]() Recorded evaluation configuration: {"Category":"Direct inference","Traceability (Comp.)":"✗","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### DataMind Overall Score: 55.06. Result ID: 6a31247bfbc373592c2e3377. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Specialized data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Qwen3-32B Overall Score: 53.8. Result ID: 6a31247bfbc373592c2e336c. [Reporting paper]() Recorded evaluation configuration: {"Category":"Direct inference","Traceability (Comp.)":"✗","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B Overall Score: 53.18. Result ID: 6a31247bfbc373592c2e336d. [Reporting paper]() Recorded evaluation configuration: {"Category":"Direct inference","Traceability (Comp.)":"✗","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### Qwen3-Coder-30B Overall Score: 51.25. Result ID: 6a31247bfbc373592c2e3373. [Reporting paper]() Recorded evaluation configuration: {"Category":"ReAct data agents","Traceability (Comp.)":"✓","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. ### GPT-5.2 Overall Score: 48.75. Result ID: 6a31247bfbc373592c2e3368. [Reporting paper]() Recorded evaluation configuration: {"Category":"Direct inference","Traceability (Comp.)":"✗","Traceability (Deriv.)":"✗"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.