# Identity Judgment on MISID Source: [Identity Judgment on MISID]() Collection index: [llms.txt]() Data updated: 2026-04-15T09:42:46.039Z Evaluation of model performance on the Identity Judgment task using the MISID dataset, measured by Identity Judgment Accuracy and Identity Reasoning 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 | Identity Judgment | | Dataset (including any stated split) | MISID | | Metric | Identity Judgment Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 29 of 29 | | 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 - [Identity Judgment Accuracy](): Higher is better; unit: PERCENT. - [Identity Reasoning Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Identity Judgment Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DeepSeek-R1 | 72.22 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-R1 | 65.38 | Not recorded | 69df1bbc7d0172140ec7badd | | Claude-Sonnet-4.5 | 61.96 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-V3 | 61.69 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 57.69 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-5.1 | 56.93 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 55.56 | Not recorded | 69df1bbc7d0172140ec7badd | | GLM-4.7 | 55.01 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 54.85 | Not recorded | 69df1bbc7d0172140ec7badd | | Gemini-3-flash | 53.85 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 53.37 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-V3 | 51.92 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 51.92 | Not recorded | 69df1bbc7d0172140ec7badd | | Claude-Sonnet-4.5 | 50.48 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 46.15 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Flash | 46.15 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-5.1 | 44.23 | Not recorded | 69df1bbc7d0172140ec7badd | | MiniMax-M2.1 | 43.29 | Not recorded | 69df1bbc7d0172140ec7badd | | GLM-4.7 | 42.31 | Not recorded | 69df1bbc7d0172140ec7badd | | MiniMax-M2.1 | 42.31 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 37.82 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-Max | 33.76 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Max | 30.77 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-235B-A22B | 28.85 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-Max | 26.92 | Not recorded | 69df1bbc7d0172140ec7badd | | Gemini-2.5-flash | 21.15 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 17.31 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Plus | 15.38 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 13.46 | Not recorded | 69df1bbc7d0172140ec7badd | ### DeepSeek-R1 Identity Judgment Accuracy: 72.22. Result ID: 69df5c8647f34ce924c87a48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### DeepSeek-R1 Identity Judgment Accuracy: 65.38. Result ID: 69df5c8647f34ce924c87a3e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5 Identity Judgment Accuracy: 61.96. Result ID: 69df5c8647f34ce924c87a47. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### DeepSeek-V3 Identity Judgment Accuracy: 61.69. Result ID: 69df5c8647f34ce924c87a49. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Grok-4-Fast Identity Judgment Accuracy: 57.69. Result ID: 69df5c8647f34ce924c87a43. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### GPT-5.1 Identity Judgment Accuracy: 56.93. Result ID: 69df5c8647f34ce924c87a4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Grok-4-Fast Identity Judgment Accuracy: 55.56. Result ID: 69df5c8647f34ce924c87a4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GLM-4.7 Identity Judgment Accuracy: 55.01. Result ID: 69df5c8647f34ce924c87a4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-4o Identity Judgment Accuracy: 54.85. Result ID: 69df5c8647f34ce924c87a4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Gemini-3-flash Identity Judgment Accuracy: 53.85. Result ID: 69df5c8647f34ce924c87a3c. [Reporting paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Grok-4-Fast Identity Judgment Accuracy: 53.37. Result ID: 69df5c8647f34ce924c87a35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### DeepSeek-V3 Identity Judgment Accuracy: 51.92. Result ID: 69df5c8647f34ce924c87a3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### GPT-4o Identity Judgment Accuracy: 51.92. Result ID: 69df5c8647f34ce924c87a41. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5 Identity Judgment Accuracy: 50.48. Result ID: 69df5c8647f34ce924c87a3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### GPT-4o Identity Judgment Accuracy: 46.15. Result ID: 69df5c8647f34ce924c87a34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-VL-Flash Identity Judgment Accuracy: 46.15. Result ID: 69df5c8647f34ce924c87a37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### GPT-5.1 Identity Judgment Accuracy: 44.23. Result ID: 69df5c8647f34ce924c87a42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Identity Judgment Accuracy: 43.29. Result ID: 69df5c8647f34ce924c87a4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GLM-4.7 Identity Judgment Accuracy: 42.31. Result ID: 69df5c8647f34ce924c87a40. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Identity Judgment Accuracy: 42.31. Result ID: 69df5c8647f34ce924c87a44. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Identity Judgment Accuracy: 37.82. Result ID: 69df5c8647f34ce924c87a50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Qwen3-Max Identity Judgment Accuracy: 33.76. Result ID: 69df5c8647f34ce924c87a4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Qwen3-VL-Max Identity Judgment Accuracy: 30.77. Result ID: 69df5c8647f34ce924c87a38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-VL-235B-A22B Identity Judgment Accuracy: 28.85. Result ID: 69df5c8647f34ce924c87a36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-Max Identity Judgment Accuracy: 26.92. Result ID: 69df5c8647f34ce924c87a45. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Gemini-2.5-flash Identity Judgment Accuracy: 21.15. Result ID: 69df5c8647f34ce924c87a3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Identity Judgment Accuracy: 17.31. Result ID: 69df5c8647f34ce924c87a46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3-VL-Plus Identity Judgment Accuracy: 15.38. Result ID: 69df5c8647f34ce924c87a39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Identity Judgment Accuracy: 13.46. Result ID: 69df5c8647f34ce924c87a3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.