# Emotion Analysis on MISID Source: [Emotion Analysis on MISID]() Collection index: [llms.txt]() Data updated: 2026-04-15T09:42:45.970Z Evaluation of Emotion Analysis performance on the MISID dataset, reporting Emotion State Accuracy and Emotion Intensity 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 | Emotion Analysis | | Dataset (including any stated split) | MISID | | Metric | Emotion State 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 - [Emotion State Accuracy](): Higher is better; unit: PERCENT. - [Emotion Intensity Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Emotion State Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Claude-Sonnet-4.5 | 90.75 | Not recorded | 69df1bbc7d0172140ec7badd | | Claude-Sonnet-4.5 | 89.01 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 88.92 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 87.32 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 87.16 | Not recorded | 69df1bbc7d0172140ec7badd | | Gemini-3-flash | 87.09 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 86.59 | Not recorded | 69df1bbc7d0172140ec7badd | | Grok-4-Fast | 86.21 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-5.1 | 84.14 | Not recorded | 69df1bbc7d0172140ec7badd | | GLM-4.7 | 83.79 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3.5-Plus | 83.78 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-R1 | 83.73 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-R1 | 83.45 | Not recorded | 69df1bbc7d0172140ec7badd | | GLM-4.7 | 83.39 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-5.1 | 82.73 | Not recorded | 69df1bbc7d0172140ec7badd | | Gemini-2.5-flash | 82.55 | Not recorded | 69df1bbc7d0172140ec7badd | | MiniMax-M2.1 | 82.02 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 80.28 | Not recorded | 69df1bbc7d0172140ec7badd | | MiniMax-M2.1 | 80.08 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-Max | 80.03 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 79.87 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-235B-A22B | 79.05 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-Max | 77.18 | Not recorded | 69df1bbc7d0172140ec7badd | | GPT-4o | 76.43 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Max | 74.05 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Plus | 72.83 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-V3 | 69.53 | Not recorded | 69df1bbc7d0172140ec7badd | | Qwen3-VL-Flash | 69.23 | Not recorded | 69df1bbc7d0172140ec7badd | | DeepSeek-V3 | 66.91 | Not recorded | 69df1bbc7d0172140ec7badd | ### Claude-Sonnet-4.5 Emotion State Accuracy: 90.75. Result ID: 69df5c8647f34ce924c87a0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5 Emotion State Accuracy: 89.01. Result ID: 69df5c8647f34ce924c87a03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Grok-4-Fast Emotion State Accuracy: 88.92. Result ID: 69df5c8647f34ce924c87a13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Emotion State Accuracy: 87.32. Result ID: 69df5c8647f34ce924c87a0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Emotion State Accuracy: 87.16. Result ID: 69df5c8647f34ce924c87a16. [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 Emotion State Accuracy: 87.09. Result ID: 69df5c8647f34ce924c87a02. [Reporting paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Grok-4-Fast Emotion State Accuracy: 86.59. Result ID: 69df5c8647f34ce924c87a09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Grok-4-Fast Emotion State Accuracy: 86.21. Result ID: 69df5c8647f34ce924c879fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### GPT-5.1 Emotion State Accuracy: 84.14. Result ID: 69df5c8647f34ce924c87a12. [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 Emotion State Accuracy: 83.79. Result ID: 69df5c8647f34ce924c87a06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Emotion State Accuracy: 83.78. Result ID: 69df5c8647f34ce924c87a00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### DeepSeek-R1 Emotion State Accuracy: 83.73. Result ID: 69df5c8647f34ce924c87a0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### DeepSeek-R1 Emotion State Accuracy: 83.45. Result ID: 69df5c8647f34ce924c87a04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### GLM-4.7 Emotion State Accuracy: 83.39. Result ID: 69df5c8647f34ce924c87a10. [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 Emotion State Accuracy: 82.73. Result ID: 69df5c8647f34ce924c87a08. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Gemini-2.5-flash Emotion State Accuracy: 82.55. Result ID: 69df5c8647f34ce924c87a01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Emotion State Accuracy: 82.02. Result ID: 69df5c8647f34ce924c87a14. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-4o Emotion State Accuracy: 80.28. Result ID: 69df5c8647f34ce924c87a07. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### MiniMax-M2.1 Emotion State Accuracy: 80.08. Result ID: 69df5c8647f34ce924c87a0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### Qwen3-Max Emotion State Accuracy: 80.03. Result ID: 69df5c8647f34ce924c87a15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### GPT-4o Emotion State Accuracy: 79.87. Result ID: 69df5c8647f34ce924c87a11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only","Assistance Framework":"FRACTAM"}. This record does not assert independent reproduction. ### Qwen3-VL-235B-A22B Emotion State Accuracy: 79.05. Result ID: 69df5c8647f34ce924c879fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-Max Emotion State Accuracy: 77.18. Result ID: 69df5c8647f34ce924c87a0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Text-only"}. This record does not assert independent reproduction. ### GPT-4o Emotion State Accuracy: 76.43. Result ID: 69df5c8647f34ce924c879fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-VL-Max Emotion State Accuracy: 74.05. Result ID: 69df5c8647f34ce924c879fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### Qwen3-VL-Plus Emotion State Accuracy: 72.83. Result ID: 69df5c8647f34ce924c879ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### DeepSeek-V3 Emotion State Accuracy: 69.53. Result ID: 69df5c8647f34ce924c87a0f. [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 Emotion State Accuracy: 69.23. Result ID: 69df5c8647f34ce924c879fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"Video + Text"}. This record does not assert independent reproduction. ### DeepSeek-V3 Emotion State Accuracy: 66.91. Result ID: 69df5c8647f34ce924c87a05. [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.