# Hidden Intent Inference on MISID Source: [Hidden Intent Inference on MISID]() Collection index: [llms.txt]() Data updated: 2026-04-15T09:42:46.097Z Evaluation of model performance on the Hidden Intent Inference task using the MISID dataset, measured by Hidden Intent Inference 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 | Hidden Intent Inference | | Dataset (including any stated split) | MISID | | Metric | Hidden Intent Inference Score | | Unit | SCALAR | | 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 - [Hidden Intent Inference Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Hidden Intent Inference Score | Result date | Report paper | | --- | --- | --- | --- | | Claude-Sonnet-4.5 | 53.27 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-5.1 | 52.83 | Not recorded | 69df1bbc7d0172140ec7badd | | Gemini-3-flash | 49.52 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-V3 | 48.02 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 46.09 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-R1 | 45.59 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-V3 | 44.23 | Not recorded | 69df1bbc7d0172140ec7badd | | Claude-Sonnet-4.5 | 43.35 | Not recorded | 69df1bbc7d0172140ec7badd | | GLM-4.7 | 43.04 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 41.23 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 40.85 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 40.01 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 39.77 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 38.84 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-5.1 | 36.46 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-R1 | 36.35 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 32.69 | Not recorded | 69df1bbc7d0172140ec7badd | | GLM-4.7 | 31.96 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-Max | 30.44 | Not recorded | 69df1bbc7d0172140ec7badd | | MiniMax-M2.1 | 29.72 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Flash | 28.27 | Not recorded | 69df1bbc7d0172140ec7badd | | Gemini-2.5-flash | 26.85 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Max | 23.42 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Plus | 23.27 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 23.27 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-Max | 22.85 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 22.12 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-235B-A22B | 21.69 | Not recorded | 69df1bbc7d0172140ec7badd | | MiniMax-M2.1 | 21.69 | Not recorded | 69df1bbc7d0172140ec7badd | ### Claude-Sonnet-4.5 Hidden Intent Inference Score: 53.27. Result ID: 69df5c8647f34ce924c87a81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-5.1 Hidden Intent Inference Score: 52.83. Result ID: 69df5c8647f34ce924c87a86. [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 Hidden Intent Inference Score: 49.52. Result ID: 69df5c8647f34ce924c87a76. [Reporting paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### DeepSeek-V3 Hidden Intent Inference Score: 48.02. Result ID: 69df5c8647f34ce924c87a83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-4o Hidden Intent Inference Score: 46.09. Result ID: 69df5c8647f34ce924c87a85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### DeepSeek-R1 Hidden Intent Inference Score: 45.59. Result ID: 69df5c8647f34ce924c87a82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### DeepSeek-V3 Hidden Intent Inference Score: 44.23. Result ID: 69df5c8647f34ce924c87a79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5 Hidden Intent Inference Score: 43.35. Result ID: 69df5c8647f34ce924c87a77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### GLM-4.7 Hidden Intent Inference Score: 43.04. Result ID: 69df5c8647f34ce924c87a84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-4o Hidden Intent Inference Score: 41.23. Result ID: 69df5c8647f34ce924c87a7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Grok-4-Fast Hidden Intent Inference Score: 40.85. Result ID: 69df5c8647f34ce924c87a7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Grok-4-Fast Hidden Intent Inference Score: 40.01. Result ID: 69df5c8647f34ce924c87a87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-4o Hidden Intent Inference Score: 39.77. Result ID: 69df5c8647f34ce924c87a6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Hidden Intent Inference Score: 38.84. Result ID: 69df5c8647f34ce924c87a8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-5.1 Hidden Intent Inference Score: 36.46. Result ID: 69df5c8647f34ce924c87a7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### DeepSeek-R1 Hidden Intent Inference Score: 36.35. Result ID: 69df5c8647f34ce924c87a78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Grok-4-Fast Hidden Intent Inference Score: 32.69. Result ID: 69df5c8647f34ce924c87a6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### GLM-4.7 Hidden Intent Inference Score: 31.96. Result ID: 69df5c8647f34ce924c87a7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3-Max Hidden Intent Inference Score: 30.44. Result ID: 69df5c8647f34ce924c87a89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Hidden Intent Inference Score: 29.72. Result ID: 69df5c8647f34ce924c87a88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Qwen3-VL-Flash Hidden Intent Inference Score: 28.27. Result ID: 69df5c8647f34ce924c87a71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Gemini-2.5-flash Hidden Intent Inference Score: 26.85. Result ID: 69df5c8647f34ce924c87a75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-VL-Max Hidden Intent Inference Score: 23.42. Result ID: 69df5c8647f34ce924c87a72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-VL-Plus Hidden Intent Inference Score: 23.27. Result ID: 69df5c8647f34ce924c87a73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Hidden Intent Inference Score: 23.27. Result ID: 69df5c8647f34ce924c87a80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3-Max Hidden Intent Inference Score: 22.85. Result ID: 69df5c8647f34ce924c87a7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Hidden Intent Inference Score: 22.12. Result ID: 69df5c8647f34ce924c87a74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-VL-235B-A22B Hidden Intent Inference Score: 21.69. Result ID: 69df5c8647f34ce924c87a70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Hidden Intent Inference Score: 21.69. Result ID: 69df5c8647f34ce924c87a7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.