# Judicial Conflict Resolution on AgentsCourt + China Judgements Online

Source: [Judicial Conflict Resolution on AgentsCourt + China Judgements Online](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T12:38:26.350Z

Evaluation of model performance on resolving judicial conflicts using the combined AgentsCourt and China Judgements Online datasets, focusing on legal article citation, charge accuracy, and sentencing 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 | Judicial Conflict Resolution |
| Dataset (including any stated split) | AgentsCourt + China Judgements Online |
| Metric | Legal Article Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Legal Article Precision](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online.md?metric=Legal%20Article%20Precision>): Higher is better; unit: PERCENT.

- [Legal Article Recall](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online.md?metric=Legal%20Article%20Recall>): Higher is better; unit: PERCENT.

- [Legal Article F1-score](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online.md?metric=Legal%20Article%20F1-score>): Higher is better; unit: PERCENT.

- [Charge Accuracy](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online.md?metric=Charge%20Accuracy>): Higher is better; unit: PERCENT.

- [Sentence Accuracy](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online.md?metric=Sentence%20Accuracy>): Higher is better; unit: PERCENT.

- [Fine-grained Accuracy](<https://www.sota2.com/research/sota/judicial-conflict-resolution-on-agentscourt-plus-china-judgements-online.md?metric=Fine-grained%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Legal Article Precision | Result date | Report paper |
| --- | --- | --- | --- |
| BEACOF | 73.33 | Not recorded | 69c60ef00636e5bf4afc8410 |
| MAD | 69.08 | Not recorded | 69c60ef00636e5bf4afc8410 |
| BEACOF | 67.43 | Not recorded | 69c60ef00636e5bf4afc8410 |
| MAD | 66.59 | Not recorded | 69c60ef00636e5bf4afc8410 |
| BEACOF | 43.87 | Not recorded | 69c60ef00636e5bf4afc8410 |
| CAMEL | 43.03 | Not recorded | 69c60ef00636e5bf4afc8410 |
| CAMEL | 42.9 | Not recorded | 69c60ef00636e5bf4afc8410 |
| CAMEL | 33.43 | Not recorded | 69c60ef00636e5bf4afc8410 |
| MAD | 31.08 | Not recorded | 69c60ef00636e5bf4afc8410 |

### BEACOF

Legal Article Precision: 73.33. Result ID: 69c6795247f34ce924b04e7e.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### MAD

Legal Article Precision: 69.08. Result ID: 69c6795247f34ce924b04e7d.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75171e209131cea65abb.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### BEACOF

Legal Article Precision: 67.43. Result ID: 69c6795247f34ce924b04e7b.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

Recorded evaluation configuration: {"Base Model":"Gemma3-12B"}. This record does not assert independent reproduction.

### MAD

Legal Article Precision: 66.59. Result ID: 69c6795247f34ce924b04e7a.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75171e209131cea65abb.md>)

Recorded evaluation configuration: {"Base Model":"Gemma3-12B"}. This record does not assert independent reproduction.

### BEACOF

Legal Article Precision: 43.87. Result ID: 69c6795247f34ce924b04e78.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

Recorded evaluation configuration: {"Base Model":"Llama3.1-8B-Instruct"}. This record does not assert independent reproduction.

### CAMEL

Legal Article Precision: 43.03. Result ID: 69c6795247f34ce924b04e76.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1bf.md>)

Recorded evaluation configuration: {"Base Model":"Llama3.1-8B-Instruct"}. This record does not assert independent reproduction.

### CAMEL

Legal Article Precision: 42.9. Result ID: 69c6795247f34ce924b04e79.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1bf.md>)

Recorded evaluation configuration: {"Base Model":"Gemma3-12B"}. This record does not assert independent reproduction.

### CAMEL

Legal Article Precision: 33.43. Result ID: 69c6795247f34ce924b04e7c.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1bf.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### MAD

Legal Article Precision: 31.08. Result ID: 69c6795247f34ce924b04e77.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ef00636e5bf4afc8410.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75171e209131cea65abb.md>)

Recorded evaluation configuration: {"Base Model":"Llama3.1-8B-Instruct"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
