# Event Logical Reasoning on BizFinBench v2

Source: [Event Logical Reasoning on BizFinBench v2](<https://www.sota2.com/research/sota/event-logical-reasoning-on-bizfinbench-v2>)

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

Data updated: 2026-04-13T09:57:00.482Z

Evaluation of model performance on Event Logical Reasoning tasks using the BizFinBench v2 dataset, reporting 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 | Event Logical Reasoning |
| Dataset (including any stated split) | BizFinBench v2 |
| Metric | Accuracy |
| Unit | PERCENT |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/event-logical-reasoning-on-bizfinbench-v2.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Fine-tuning | 73.34 | Not recorded | 69dc78a17d0172140ec78beb |
| KNN | 51.67 | Not recorded | 69dc78a17d0172140ec78beb |
| AIR | 51.67 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy GEPA | 46.67 | Not recorded | 69dc78a17d0172140ec78beb |
| Initial prompt | 45 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy MIPROv2 | 43.33 | Not recorded | 69dc78a17d0172140ec78beb |
| TextGrad | 43.33 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy BootstrapFewShot (#3) | 35 | Not recorded | 69dc78a17d0172140ec78beb |

### Fine-tuning

Accuracy: 73.34. Result ID: 69dcbdd547f34ce924c4201b.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) Base Model":"247908 / 7560","Inference Tokens (input / output) Base Model":"28477 / 856"}. This record does not assert independent reproduction.

### KNN

Accuracy: 51.67. Result ID: 69dcbdd547f34ce924c4201a.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Inference Tokens (input / output) Base Model":"41249 / 895"}. This record does not assert independent reproduction.

### AIR

Accuracy: 51.67. Result ID: 69dcbdd547f34ce924c42020.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) Embed Model":"65923 / -","Train Tokens (input / output) Base Model":"453192 / 3008","Train Tokens (input / output) Reflection Model":"58716 / 65583","Inference Tokens (input / output) Base Model":"292237 / 1036"}. This record does not assert independent reproduction.

### DSPy GEPA

Accuracy: 46.67. Result ID: 69dcbdd547f34ce924c4201e.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a3a1e209131cea81ee3.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) Base Model":"1998619 / 23064","Train Tokens (input / output) Reflection Model":"37111 / 26706","Inference Tokens (input / output) Base Model":"170138 / 1396"}. This record does not assert independent reproduction.

### Initial prompt

Accuracy: 45. Result ID: 69dcbdd547f34ce924c42019.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Inference Tokens (input / output) Base Model":"28477 / 1036"}. This record does not assert independent reproduction.

### DSPy MIPROv2

Accuracy: 43.33. Result ID: 69dcbdd547f34ce924c4201d.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75121e209131cea65828.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) Base Model":"1616492 / 38339","Inference Tokens (input / output) Base Model":"72278 / 1456"}. This record does not assert independent reproduction.

### TextGrad

Accuracy: 43.33. Result ID: 69dcbdd547f34ce924c4201f.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73981e209131cea5d7cd.md>)

[Implementation](<https://github.com/zou-group/textgrad>)

Recorded evaluation configuration: {"Train Tokens (input / output) Base Model":"728850 / 78210","Train Tokens (input / output) Reflection Model":"7589 / 112655","Inference Tokens (input / output) Base Model":"51157 / 976"}. This record does not assert independent reproduction.

### DSPy BootstrapFewShot (#3)

Accuracy: 35. Result ID: 69dcbdd547f34ce924c4201c.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d01e209131cea4d60e.md>)

[Implementation](<https://github.com/stanfordnlp/dspy>)

Recorded evaluation configuration: {"Train Tokens (input / output) Base Model":"17001 / 344","Inference Tokens (input / output) Base Model":"72338 / 1456"}. This record does not assert independent reproduction.

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