# Legal Judgment Prediction on ILDC (test) Source: [Legal Judgment Prediction on ILDC (test)]() Collection index: [llms.txt]() Data updated: 2026-06-23T07:44:11.985Z Evaluation of model performance on predicting legal judgments using the test split of the ILDC dataset, measured using Accuracy, Coverage, CD-Gain, CD-Cost, and Net-Gain metrics. 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 | Legal Judgment Prediction | | Dataset (including any stated split) | ILDC (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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. - [Coverage](): Higher is better; unit: PERCENT. - [CD-Gain](): Higher is better; unit: PERCENT. - [CD-Cost](): Lower is better; unit: PERCENT. - [Net-Gain](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FC-Last3-RFN | 84.52 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Mid3-RFN | 79.15 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Mid3-RFN | 78.88 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Last3-RFN | 78.73 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Mid3-RFN | 78.06 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Last3-RFN | 77.29 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Last3-REV | 75.74 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Mid3-RFN | 74.87 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Last3-REV | 74.85 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Mid3-REV | 74.35 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Last3-RFN | 74.17 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Last3-RFN | 73.33 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Mid3-REV | 73.15 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Mid3-REV | 72.85 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Last3-REV | 72.78 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Mid3-REV | 72.64 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Last3-RFN | 71.8 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Last3-REV | 70.3 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Last3-REV | 68.07 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Last3-REV | 66.35 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Mid3-RFN | 65.64 | Not recorded | 6a3a1317206542251d7c6ffe | | Attn-Mid3-REV | 63.16 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Mid3-RFN | 60.17 | Not recorded | 6a3a1317206542251d7c6ffe | | FC-Mid3-REV | 59.86 | Not recorded | 6a3a1317206542251d7c6ffe | | LLM-only | 59.2 | Not recorded | 6a3a1317206542251d7c6ffe | | LLM-only | 58.78 | Not recorded | 6a3a1317206542251d7c6ffe | | LLM-only | 54.84 | Not recorded | 6a3a1317206542251d7c6ffe | ### FC-Last3-RFN Accuracy: 84.52. Result ID: 6a3a38b4fbc373592c34279b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Refrain"}. This record does not assert independent reproduction. ### Attn-Mid3-RFN Accuracy: 79.15. Result ID: 6a3a38b4fbc373592c3427a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### Attn-Mid3-RFN Accuracy: 78.88. Result ID: 6a3a38b4fbc373592c34279d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Refrain"}. This record does not assert independent reproduction. ### Attn-Last3-RFN Accuracy: 78.73. Result ID: 6a3a38b4fbc373592c34279f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Refrain"}. This record does not assert independent reproduction. ### FC-Mid3-RFN Accuracy: 78.06. Result ID: 6a3a38b4fbc373592c342799. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Refrain"}. This record does not assert independent reproduction. ### FC-Last3-RFN Accuracy: 77.29. Result ID: 6a3a38b4fbc373592c3427a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### FC-Last3-REV Accuracy: 75.74. Result ID: 6a3a38b4fbc373592c3427ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### FC-Mid3-RFN Accuracy: 74.87. Result ID: 6a3a38b4fbc373592c3427a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### FC-Last3-REV Accuracy: 74.85. Result ID: 6a3a38b4fbc373592c34279c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Reverse"}. This record does not assert independent reproduction. ### Attn-Mid3-REV Accuracy: 74.35. Result ID: 6a3a38b4fbc373592c34279e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Reverse"}. This record does not assert independent reproduction. ### FC-Last3-RFN Accuracy: 74.17. Result ID: 6a3a38b4fbc373592c3427ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### Attn-Last3-RFN Accuracy: 73.33. Result ID: 6a3a38b4fbc373592c3427b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### FC-Mid3-REV Accuracy: 73.15. Result ID: 6a3a38b4fbc373592c3427a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### FC-Mid3-REV Accuracy: 72.85. Result ID: 6a3a38b4fbc373592c34279a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Reverse"}. This record does not assert independent reproduction. ### Attn-Last3-REV Accuracy: 72.78. Result ID: 6a3a38b4fbc373592c3427b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### Attn-Mid3-REV Accuracy: 72.64. Result ID: 6a3a38b4fbc373592c3427a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### Attn-Last3-RFN Accuracy: 71.8. Result ID: 6a3a38b4fbc373592c3427a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### FC-Last3-REV Accuracy: 70.3. Result ID: 6a3a38b4fbc373592c3427a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### Attn-Last3-REV Accuracy: 68.07. Result ID: 6a3a38b4fbc373592c3427a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b","Setting":"Reverse"}. This record does not assert independent reproduction. ### Attn-Last3-REV Accuracy: 66.35. Result ID: 6a3a38b4fbc373592c3427a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### Attn-Mid3-RFN Accuracy: 65.64. Result ID: 6a3a38b4fbc373592c3427af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### Attn-Mid3-REV Accuracy: 63.16. Result ID: 6a3a38b4fbc373592c3427b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### FC-Mid3-RFN Accuracy: 60.17. Result ID: 6a3a38b4fbc373592c3427ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Refrain"}. This record does not assert independent reproduction. ### FC-Mid3-REV Accuracy: 59.86. Result ID: 6a3a38b4fbc373592c3427ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b","Setting":"Reverse"}. This record does not assert independent reproduction. ### LLM-only Accuracy: 59.2. Result ID: 6a3a38b4fbc373592c3427aa. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-7b"}. This record does not assert independent reproduction. ### LLM-only Accuracy: 58.78. Result ID: 6a3a38b4fbc373592c3427a1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7b"}. This record does not assert independent reproduction. ### LLM-only Accuracy: 54.84. Result ID: 6a3a38b4fbc373592c342798. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-8b"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.