# Extractive Question Answering for Causal Relations on FinCausal English 2026 (test)

Source: [Extractive Question Answering for Causal Relations on FinCausal English 2026 (test)](<https://www.sota2.com/research/sota/extractive-question-answering-for-causal-relations-on-fincausal-english-2026-test>)

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

Data updated: 2026-06-29T06:26:09.129Z

Evaluation of model performance on the test split of the FinCausal English 2026 dataset, focusing on Extractive Question Answering for Causal Relations, typically measured using an LLM Judge 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 | Extractive Question Answering for Causal Relations |
| Dataset (including any stated split) | FinCausal English 2026 (test) |
| Metric | LLM Judge Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [LLM Judge Score](<https://www.sota2.com/research/sota/extractive-question-answering-for-causal-relations-on-fincausal-english-2026-test.md?metric=LLM%20Judge%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | LLM Judge Score | Result date | Report paper |
| --- | --- | --- | --- |
| HSA\_CORAL | 4.814 | Not recorded | 6a41fc11206542251d7ccae3 |
| GPT-5.2 | 4.76 | Not recorded | 6a41fc11206542251d7ccae3 |
| GPT-4.1 mini | 4.756 | Not recorded | 6a41fc11206542251d7ccae3 |
| GPT-4.1 mini | 4.721 | Not recorded | 6a41fc11206542251d7ccae3 |
| GPT-3.5 turbo | 4.704 | Not recorded | 6a41fc11206542251d7ccae3 |
| BART Facebook Base | 4.12 | Not recorded | 6a41fc11206542251d7ccae3 |
| Llama-3.1 8B | 4.02 | Not recorded | 6a41fc11206542251d7ccae3 |
| BERT Base Multilingual | 3.98 | Not recorded | 6a41fc11206542251d7ccae3 |

### HSA\_CORAL

LLM Judge Score: 4.814. Result ID: 6a420ffafbc373592c8651fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

Recorded evaluation configuration: {"Base Model":"GPT-4.1 mini","Fine-tuned":"yes","Corpus":"Multilingual (en+es)"}. This record does not assert independent reproduction.

### GPT-5.2

LLM Judge Score: 4.76. Result ID: 6a420ffafbc373592c8651fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

Recorded evaluation configuration: {"Fine-tuned":"no","Corpus":"-"}. This record does not assert independent reproduction.

### GPT-4.1 mini

LLM Judge Score: 4.756. Result ID: 6a420ffafbc373592c8651f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

Recorded evaluation configuration: {"Fine-tuned":"yes","Corpus":"Monolingual (en)"}. This record does not assert independent reproduction.

### GPT-4.1 mini

LLM Judge Score: 4.721. Result ID: 6a420ffafbc373592c8651f9.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

Recorded evaluation configuration: {"Fine-tuned":"yes","Corpus":"Monolingual (es)"}. This record does not assert independent reproduction.

### GPT-3.5 turbo

LLM Judge Score: 4.704. Result ID: 6a420ffafbc373592c8651f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

Recorded evaluation configuration: {"Fine-tuned":"no","Corpus":"-"}. This record does not assert independent reproduction.

### BART Facebook Base

LLM Judge Score: 4.12. Result ID: 6a420ffafbc373592c8651f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66921e209131cea10fff.md>)

Recorded evaluation configuration: {"Fine-tuned":"yes","Corpus":"Multilingual (en+es)"}. This record does not assert independent reproduction.

### Llama-3.1 8B

LLM Judge Score: 4.02. Result ID: 6a420ffafbc373592c8651f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

Recorded evaluation configuration: {"Fine-tuned":"yes","Corpus":"Multilingual (en+es)"}. This record does not assert independent reproduction.

### BERT Base Multilingual

LLM Judge Score: 3.98. Result ID: 6a420ffafbc373592c8651f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Fine-tuned":"yes","Corpus":"Multilingual (en+es)"}. This record does not assert independent reproduction.

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