# Deep Research on KDR-Bench Source: [Deep Research on KDR-Bench]() Collection index: [llms.txt]() Data updated: 2026-04-10T07:38:48.581Z Evaluation of model performance on the Deep Research task using the KDR-Bench dataset, measured across dimensions such as Comprehensiveness, Coherence, Depth, Readability, and Key findings support. 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 | Deep Research | | Dataset (including any stated split) | KDR-Bench | | Metric | Average Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Average Score](): Higher is better; unit: SCALAR. - [Comprehensiveness Score](): Higher is better; unit: SCALAR. - [Depth Score](): Higher is better; unit: SCALAR. - [Coherence Score](): Higher is better; unit: SCALAR. - [Readability Score](): Higher is better; unit: SCALAR. - [Main Score](): Higher is better; unit: SCALAR. - [Key Findings Score](): Higher is better; unit: SCALAR. - [Support Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | Gemini | 50.2 | Not recorded | 69d883ef7d0172140ec778da | | HKA | 48.4 | Not recorded | 69d883ef7d0172140ec778da | | Perplexity | 46.5 | Not recorded | 69d883ef7d0172140ec778da | | ThinkDepth | 46.3 | Not recorded | 69d883ef7d0172140ec778da | | ThinkDepth | 46.1 | Not recorded | 69d883ef7d0172140ec778da | | ThinkDepth | 46.1 | Not recorded | 69d883ef7d0172140ec778da | | Enterprise | 46 | Not recorded | 69d883ef7d0172140ec778da | | LangChain | 44.9 | Not recorded | 69d883ef7d0172140ec778da | | LangChain | 44.8 | Not recorded | 69d883ef7d0172140ec778da | | Minimax-M2 | 44.7 | Not recorded | 69d883ef7d0172140ec778da | | Qwen3-Max | 44.6 | Not recorded | 69d883ef7d0172140ec778da | | Grok | 44.5 | Not recorded | 69d883ef7d0172140ec778da | | LangChain | 44.4 | Not recorded | 69d883ef7d0172140ec778da | | Tongyi | 41.8 | Not recorded | 69d883ef7d0172140ec778da | | OpenAI | 41.3 | Not recorded | 69d883ef7d0172140ec778da | | GLM4.6 | 40.8 | Not recorded | 69d883ef7d0172140ec778da | | Hunyuan2.0 | 40.6 | Not recorded | 69d883ef7d0172140ec778da | ### Gemini Average Score: 50.2. Result ID: 69d8a84847f34ce924c13496. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Closed-source DR Agents"}. This record does not assert independent reproduction. ### HKA Average Score: 48.4. Result ID: 69d8a84847f34ce924c1349f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone LLM":"Qwen3-235B-A22B-Instruct-2507","Framework":"LangGraph"}. This record does not assert independent reproduction. ### Perplexity Average Score: 46.5. Result ID: 69d8a84847f34ce924c13494. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Closed-source DR Agents"}. This record does not assert independent reproduction. ### ThinkDepth Average Score: 46.3. Result ID: 69d8a84847f34ce924c1349e. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents","Search Setting":"Hybrid Search"}. This record does not assert independent reproduction. ### ThinkDepth Average Score: 46.1. Result ID: 69d8a84847f34ce924c1349c. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents","Search Setting":"Web Search"}. This record does not assert independent reproduction. ### ThinkDepth Average Score: 46.1. Result ID: 69d8a84847f34ce924c1349d. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents","Search Setting":"Table Search"}. This record does not assert independent reproduction. ### Enterprise Average Score: 46. Result ID: 69d8a84847f34ce924c13498. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents"}. This record does not assert independent reproduction. ### LangChain Average Score: 44.9. Result ID: 69d8a84847f34ce924c1349a. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents","Search Setting":"Table Search"}. This record does not assert independent reproduction. ### LangChain Average Score: 44.8. Result ID: 69d8a84847f34ce924c1349b. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents","Search Setting":"Hybrid Search"}. This record does not assert independent reproduction. ### Minimax-M2 Average Score: 44.7. Result ID: 69d8a84847f34ce924c13492. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"LLM with search tools"}. This record does not assert independent reproduction. ### Qwen3-Max Average Score: 44.6. Result ID: 69d8a84847f34ce924c13491. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Agent Category":"LLM with search tools"}. This record does not assert independent reproduction. ### Grok Average Score: 44.5. Result ID: 69d8a84847f34ce924c13495. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Closed-source DR Agents"}. This record does not assert independent reproduction. ### LangChain Average Score: 44.4. Result ID: 69d8a84847f34ce924c13499. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents","Search Setting":"Web Search"}. This record does not assert independent reproduction. ### Tongyi Average Score: 41.8. Result ID: 69d8a84847f34ce924c13497. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Agent Category":"Open-source DR Agents"}. This record does not assert independent reproduction. ### OpenAI Average Score: 41.3. Result ID: 69d8a84847f34ce924c13493. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"Closed-source DR Agents"}. This record does not assert independent reproduction. ### GLM4.6 Average Score: 40.8. Result ID: 69d8a84847f34ce924c13490. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Agent Category":"LLM with search tools"}. This record does not assert independent reproduction. ### Hunyuan2.0 Average Score: 40.6. Result ID: 69d8a84847f34ce924c1348f. [Reporting paper]() Recorded evaluation configuration: {"Agent Category":"LLM with search tools"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.