# Clinical Task Execution on MedAgentBench OOD Source: [Clinical Task Execution on MedAgentBench OOD]() Collection index: [llms.txt]() Data updated: 2026-05-29T09:53:30.856Z Evaluation of model performance on Clinical Task Execution using the Out-of-Distribution (OOD) split of the MedAgentBench dataset, measured by Accuracy. 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 | Clinical Task Execution | | Dataset (including any stated split) | MedAgentBench OOD | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 35 of 35 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | GRASP | 80.6 | Not recorded | 6a191dcfdbd7150506f82a5c | | GRASP | 56.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | GRASP | 52.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | GRASP | 41.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | SkillX | 38.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | Evo-MedAgent | 31.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | GRASP | 27.2 | Not recorded | 6a191dcfdbd7150506f82a5c | | SkillX | 21.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | Evo-MedAgent | 20 | Not recorded | 6a191dcfdbd7150506f82a5c | | No skills | 18.1 | Not recorded | 6a191dcfdbd7150506f82a5c | | ExpeL | 17.2 | Not recorded | 6a191dcfdbd7150506f82a5c | | Seq. Memory | 16.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | Batch Memory | 16.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | Evo-MedAgent | 15.6 | Not recorded | 6a191dcfdbd7150506f82a5c | | Seq. Memory | 15.6 | Not recorded | 6a191dcfdbd7150506f82a5c | | Batch Memory | 13 | Not recorded | 6a191dcfdbd7150506f82a5c | | ExpeL | 12 | Not recorded | 6a191dcfdbd7150506f82a5c | | ExpeL | 11.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | Seq. Memory | 8.9 | Not recorded | 6a191dcfdbd7150506f82a5c | | No skills | 8.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | Seq. Memory | 8.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | Batch Memory | 8.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | SkillX | 6.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | Batch Memory | 3.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | SkillX | 3.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | No skills | 3.1 | Not recorded | 6a191dcfdbd7150506f82a5c | | ExpeL | 2.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | Batch Memory | 2.2 | Not recorded | 6a191dcfdbd7150506f82a5c | | No skills | 1.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | Evo-MedAgent | 1.7 | Not recorded | 6a191dcfdbd7150506f82a5c | | Seq. Memory | 0.6 | Not recorded | 6a191dcfdbd7150506f82a5c | | ExpeL | 0.6 | Not recorded | 6a191dcfdbd7150506f82a5c | | Evo-MedAgent | 0.6 | Not recorded | 6a191dcfdbd7150506f82a5c | | No skills | 0.3 | Not recorded | 6a191dcfdbd7150506f82a5c | | SkillX | 0 | Not recorded | 6a191dcfdbd7150506f82a5c | ### GRASP Accuracy: 80.6. Result ID: 6a1961e3fbc373592c142f28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-5.4 (low)"}. This record does not assert independent reproduction. ### GRASP Accuracy: 56.3. Result ID: 6a1961e3fbc373592c142f0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"gpt-oss-120b"}. This record does not assert independent reproduction. ### GRASP Accuracy: 52.3. Result ID: 6a1961e3fbc373592c142f13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek V4 Flash"}. This record does not assert independent reproduction. ### GRASP Accuracy: 41.7. Result ID: 6a1961e3fbc373592c142f1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Lite"}. This record does not assert independent reproduction. ### SkillX Accuracy: 38.3. Result ID: 6a1961e3fbc373592c142f19. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Lite"}. This record does not assert independent reproduction. ### Evo-MedAgent Accuracy: 31.3. Result ID: 6a1961e3fbc373592c142f0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"gpt-oss-120b"}. This record does not assert independent reproduction. ### GRASP Accuracy: 27.2. Result ID: 6a1961e3fbc373592c142f21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4.1"}. This record does not assert independent reproduction. ### SkillX Accuracy: 21.3. Result ID: 6a1961e3fbc373592c142f0b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"gpt-oss-120b"}. This record does not assert independent reproduction. ### Evo-MedAgent Accuracy: 20. Result ID: 6a1961e3fbc373592c142f11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek V4 Flash"}. This record does not assert independent reproduction. ### No skills Accuracy: 18.1. Result ID: 6a1961e3fbc373592c142f14. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Lite"}. This record does not assert independent reproduction. ### ExpeL Accuracy: 17.2. Result ID: 6a1961e3fbc373592c142f17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Lite"}. This record does not assert independent reproduction. ### Seq. Memory Accuracy: 16.7. Result ID: 6a1961e3fbc373592c142f07. [Reporting paper]() Recorded evaluation configuration: {"Model":"gpt-oss-120b"}. This record does not assert independent reproduction. ### Batch Memory Accuracy: 16.7. Result ID: 6a1961e3fbc373592c142f24. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-5.4 (low)"}. This record does not assert independent reproduction. ### Evo-MedAgent Accuracy: 15.6. Result ID: 6a1961e3fbc373592c142f18. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Lite"}. This record does not assert independent reproduction. ### Seq. Memory Accuracy: 15.6. Result ID: 6a1961e3fbc373592c142f23. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-5.4 (low)"}. This record does not assert independent reproduction. ### Batch Memory Accuracy: 13. Result ID: 6a1961e3fbc373592c142f08. [Reporting paper]() Recorded evaluation configuration: {"Model":"gpt-oss-120b"}. This record does not assert independent reproduction. ### ExpeL Accuracy: 12. Result ID: 6a1961e3fbc373592c142f09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"gpt-oss-120b"}. This record does not assert independent reproduction. ### ExpeL Accuracy: 11.7. Result ID: 6a1961e3fbc373592c142f25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-5.4 (low)"}. This record does not assert independent reproduction. ### Seq. Memory Accuracy: 8.9. Result ID: 6a1961e3fbc373592c142f15. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Lite"}. This record does not assert independent reproduction. ### No skills Accuracy: 8.7. Result ID: 6a1961e3fbc373592c142f06. [Reporting paper]() Recorded evaluation configuration: {"Model":"gpt-oss-120b"}. This record does not assert independent reproduction. ### Seq. Memory Accuracy: 8.7. Result ID: 6a1961e3fbc373592c142f0e. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek V4 Flash"}. This record does not assert independent reproduction. ### Batch Memory Accuracy: 8.3. Result ID: 6a1961e3fbc373592c142f16. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Lite"}. This record does not assert independent reproduction. ### SkillX Accuracy: 6.3. Result ID: 6a1961e3fbc373592c142f12. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"DeepSeek V4 Flash"}. This record does not assert independent reproduction. ### Batch Memory Accuracy: 3.3. Result ID: 6a1961e3fbc373592c142f0f. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek V4 Flash"}. This record does not assert independent reproduction. ### SkillX Accuracy: 3.3. Result ID: 6a1961e3fbc373592c142f27. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-5.4 (low)"}. This record does not assert independent reproduction. ### No skills Accuracy: 3.1. Result ID: 6a1961e3fbc373592c142f0d. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek V4 Flash"}. This record does not assert independent reproduction. ### ExpeL Accuracy: 2.3. Result ID: 6a1961e3fbc373592c142f10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek V4 Flash"}. This record does not assert independent reproduction. ### Batch Memory Accuracy: 2.2. Result ID: 6a1961e3fbc373592c142f1d. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4.1"}. This record does not assert independent reproduction. ### No skills Accuracy: 1.7. Result ID: 6a1961e3fbc373592c142f22. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-5.4 (low)"}. This record does not assert independent reproduction. ### Evo-MedAgent Accuracy: 1.7. Result ID: 6a1961e3fbc373592c142f26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-5.4 (low)"}. This record does not assert independent reproduction. ### Seq. Memory Accuracy: 0.6. Result ID: 6a1961e3fbc373592c142f1c. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4.1"}. This record does not assert independent reproduction. ### ExpeL Accuracy: 0.6. Result ID: 6a1961e3fbc373592c142f1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4.1"}. This record does not assert independent reproduction. ### Evo-MedAgent Accuracy: 0.6. Result ID: 6a1961e3fbc373592c142f1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4.1"}. This record does not assert independent reproduction. ### No skills Accuracy: 0.3. Result ID: 6a1961e3fbc373592c142f1b. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4.1"}. This record does not assert independent reproduction. ### SkillX Accuracy: 0. Result ID: 6a1961e3fbc373592c142f20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-4.1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.