# Table-based Fact Verification on TabFact small 1.0 (test)

Source: [Table-based Fact Verification on TabFact small 1.0 (test)](<https://www.sota2.com/research/sota/table-based-fact-verification-on-tabfact-small-1-0-test>)

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

Data updated: 2026-02-26T05:28:49.167Z

Evaluation of model performance on the test split of the TabFact small 1.0 dataset for Table-based Fact Verification, 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 | Table-based Fact Verification |
| Dataset (including any stated split) | TabFact small 1.0 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| 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/table-based-fact-verification-on-tabfact-small-1-0-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PASTA w/ DATER | 93 | Not recorded | 68fa6f251e209131cea4409c |
| PASTA w/ DATER | 93 | Not recorded | 68fa6f251e209131cea4409c |
| Human | 92.1 | Not recorded | 68fa6f251e209131cea4409c |
| Human | 92.1 | Not recorded | 68fa6f251e209131cea4409c |
| PASTA | 90.8 | Not recorded | 68fa6f251e209131cea4409c |
| PASTA | 90.8 | Not recorded | 68fa6f251e209131cea4409c |
| SaMoE | 86.7 | Not recorded | 68fa6f251e209131cea4409c |
| SaMoE | 86.7 | Not recorded | 68fa6f251e209131cea4409c |
| TAPEX | 85.9 | Not recorded | 68fa6f251e209131cea4409c |
| TAPEX | 85.9 | Not recorded | 68fa6f251e209131cea4409c |
| Codex w/ DATER | 85.6 | Not recorded | 68fa6f251e209131cea4409c |
| Codex w/ DATER | 85.6 | Not recorded | 68fa6f251e209131cea4409c |
| Binder | 85.1 | Not recorded | 68fa6f251e209131cea4409c |
| Binder | 85.1 | Not recorded | 68fa6f251e209131cea4409c |
| TaPas | 83.9 | Not recorded | 68fa6f251e209131cea4409c |
| TaPas | 83.9 | Not recorded | 68fa6f251e209131cea4409c |
| SAT | 75.5 | Not recorded | 68fa6f251e209131cea4409c |
| SAT | 75.5 | Not recorded | 68fa6f251e209131cea4409c |
| LogicFactChecker | 74.3 | Not recorded | 68fa6f251e209131cea4409c |
| LogicFactChecker | 74.3 | Not recorded | 68fa6f251e209131cea4409c |
| Codex | 72.6 | Not recorded | 68fa6f251e209131cea4409c |
| Codex | 72.6 | Not recorded | 68fa6f251e209131cea4409c |
| Table-BERT | 68.1 | Not recorded | 68fa6f251e209131cea4409c |
| Table-BERT | 68.1 | Not recorded | 68fa6f251e209131cea4409c |
| Human Performance | 0.921 | Not recorded | 68fa67ba1e209131cea18269 |
| LPA-Ranking w/ Discriminator (Caption) | 0.689 | Not recorded | 68fa67ba1e209131cea18269 |

### PASTA w/ DATER

Accuracy: 93. Result ID: 699098263a6c31484901ba82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Implementation](<https://github.com/AlibabaResearch/DAMO-ConvAI>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### PASTA w/ DATER

Accuracy: 93. Result ID: 699098263a6c31484901babf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Implementation](<https://github.com/AlibabaResearch/DAMO-ConvAI>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### Human

Accuracy: 92.1. Result ID: 699098263a6c31484901ba83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Human

Accuracy: 92.1. Result ID: 699098263a6c31484901bac0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PASTA

Accuracy: 90.8. Result ID: 699098263a6c31484901ba81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dd41e209131cea3c409.md>)

[Implementation](<https://github.com/ruc-datalab/PASTA>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### PASTA

Accuracy: 90.8. Result ID: 699098263a6c31484901babe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dd41e209131cea3c409.md>)

[Implementation](<https://github.com/ruc-datalab/PASTA>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### SaMoE

Accuracy: 86.7. Result ID: 699098263a6c31484901ba80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c501e209131cea33388.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### SaMoE

Accuracy: 86.7. Result ID: 699098263a6c31484901babd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c501e209131cea33388.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### TAPEX

Accuracy: 85.9. Result ID: 699098263a6c31484901ba7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfe1e209131cea31836.md>)

[Implementation](<https://github.com/microsoft/Table-Pretraining>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### TAPEX

Accuracy: 85.9. Result ID: 699098263a6c31484901babc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfe1e209131cea31836.md>)

[Implementation](<https://github.com/microsoft/Table-Pretraining>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### Codex w/ DATER

Accuracy: 85.6. Result ID: 699098263a6c31484901ba86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Implementation](<https://github.com/AlibabaResearch/DAMO-ConvAI>)

Recorded evaluation configuration: {"Learning Paradigm":"LLM based"}. This record does not assert independent reproduction.

### Codex w/ DATER

Accuracy: 85.6. Result ID: 699098263a6c31484901bac3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Implementation](<https://github.com/AlibabaResearch/DAMO-ConvAI>)

Recorded evaluation configuration: {"Learning Paradigm":"LLM based"}. This record does not assert independent reproduction.

### Binder

Accuracy: 85.1. Result ID: 699098263a6c31484901ba84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ea71e209131cea411d9.md>)

[Implementation](<https://github.com/hkunlp/binder>)

Recorded evaluation configuration: {"Learning Paradigm":"LLM based"}. This record does not assert independent reproduction.

### Binder

Accuracy: 85.1. Result ID: 699098263a6c31484901bac1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ea71e209131cea411d9.md>)

[Implementation](<https://github.com/hkunlp/binder>)

Recorded evaluation configuration: {"Learning Paradigm":"LLM based"}. This record does not assert independent reproduction.

### TaPas

Accuracy: 83.9. Result ID: 699098263a6c31484901ba7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea333e0.md>)

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

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### TaPas

Accuracy: 83.9. Result ID: 699098263a6c31484901babb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c521e209131cea333e0.md>)

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

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### SAT

Accuracy: 75.5. Result ID: 699098263a6c31484901ba7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### SAT

Accuracy: 75.5. Result ID: 699098263a6c31484901baba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### LogicFactChecker

Accuracy: 74.3. Result ID: 699098263a6c31484901ba7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676e1e209131cea16227.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### LogicFactChecker

Accuracy: 74.3. Result ID: 699098263a6c31484901bab9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676e1e209131cea16227.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### Codex

Accuracy: 72.6. Result ID: 699098263a6c31484901ba85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5f1e209131cea27ced.md>)

[Implementation](<https://www.github.com/openai/human-eval>)

Recorded evaluation configuration: {"Learning Paradigm":"LLM based"}. This record does not assert independent reproduction.

### Codex

Accuracy: 72.6. Result ID: 699098263a6c31484901bac2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5f1e209131cea27ced.md>)

[Implementation](<https://www.github.com/openai/human-eval>)

Recorded evaluation configuration: {"Learning Paradigm":"LLM based"}. This record does not assert independent reproduction.

### Table-BERT

Accuracy: 68.1. Result ID: 699098263a6c31484901ba7b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ba1e209131cea18269.md>)

[Implementation](<https://github.com/wenhuchen/Table-Fact-Checking>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### Table-BERT

Accuracy: 68.1. Result ID: 699098263a6c31484901bab8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ba1e209131cea18269.md>)

[Implementation](<https://github.com/wenhuchen/Table-Fact-Checking>)

Recorded evaluation configuration: {"Learning Paradigm":"Fine-tuning based"}. This record does not assert independent reproduction.

### Human Performance

Accuracy: 0.921. Result ID: 698d42658b517eb433202d65.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67ba1e209131cea18269.md>)

Recorded evaluation configuration: {"Type":"Manual Evaluation"}. This record does not assert independent reproduction.

### LPA-Ranking w/ Discriminator (Caption)

Accuracy: 0.689. Result ID: 698d42658b517eb433202d66.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67ba1e209131cea18269.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ba1e209131cea18269.md>)

[Implementation](<https://github.com/wenhuchen/Table-Fact-Checking>)

Recorded evaluation configuration: {"Discriminator usage":"Ranking discriminator"}. This record does not assert independent reproduction.

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