# Text Classification Suite (SST2, FPB, COLA, DBpedia, EmoC, EmoS, ETHOS-SO, ETHOS-R)

Source: [Text Classification Suite (SST2, FPB, COLA, DBpedia, EmoC, EmoS, ETHOS-SO, ETHOS-R)](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r>)

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

Data updated: 2026-02-26T06:03:31.978Z

Evaluation of Text Classification performance across a suite of eight datasets, including SST-2, COLA, and others, reporting individual scores and an overall average.

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 | Text Classification |
| Dataset (including any stated split) | SST2, FPB, COLA, DBpedia, EmoC, EmoS, ETHOS-SO, ETHOS-R |
| Metric | SST2 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [SST2 Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=SST2%20Accuracy>): Higher is better; unit: PERCENT.

- [FPB Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=FPB%20Accuracy>): Higher is better; unit: PERCENT.

- [COLA Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=COLA%20Accuracy>): Higher is better; unit: PERCENT.

- [DBpedia Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=DBpedia%20Accuracy>): Higher is better; unit: PERCENT.

- [EmoC Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=EmoC%20Accuracy>): Higher is better; unit: PERCENT.

- [EmoS Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=EmoS%20Accuracy>): Higher is better; unit: PERCENT.

- [ETHOS-SO Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=ETHOS-SO%20Accuracy>): Higher is better; unit: PERCENT.

- [ETHOS-R Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=ETHOS-R%20Accuracy>): Higher is better; unit: PERCENT.

- [Overall Average Accuracy](<https://www.sota2.com/research/sota/text-classification-suite-sst2-fpb-cola-dbpedia-emoc-emos-ethos-so-ethos-r.md?metric=Overall%20Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | SST2 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Demonstration Selection Algorithm | 88.8 | Not recorded | 68fa72211e209131cea54b16 |
| Demonstration Selection Algorithm | 87.8 | Not recorded | 68fa72211e209131cea54b16 |
| Demonstration Selection Algorithm | 86.2 | Not recorded | 68fa72211e209131cea54b16 |
| Random | 84.2 | Not recorded | 68fa72211e209131cea54b16 |
| Random | 78.5 | Not recorded | 68fa72211e209131cea54b16 |
| Random | 77.1 | Not recorded | 68fa72211e209131cea54b16 |
| Demonstration Selection Algorithm | 74.2 | Not recorded | 68fa72211e209131cea54b16 |
| Random | 72.4 | Not recorded | 68fa72211e209131cea54b16 |
| Demonstration Selection Algorithm | 60.5 | Not recorded | 68fa72211e209131cea54b16 |
| Random | 57.7 | Not recorded | 68fa72211e209131cea54b16 |

### Demonstration Selection Algorithm

SST2 Accuracy: 88.8. Result ID: 699206813a6c3148490c1f84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Implementation](<https://github.com/WANGXinyiLinda/concept-based-demonstration-selection>)

Recorded evaluation configuration: {"LLM":"GPT3-c"}. This record does not assert independent reproduction.

### Demonstration Selection Algorithm

SST2 Accuracy: 87.8. Result ID: 699206813a6c3148490c1f86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Implementation](<https://github.com/WANGXinyiLinda/concept-based-demonstration-selection>)

Recorded evaluation configuration: {"LLM":"GPT-J"}. This record does not assert independent reproduction.

### Demonstration Selection Algorithm

SST2 Accuracy: 86.2. Result ID: 699206813a6c3148490c1f82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Implementation](<https://github.com/WANGXinyiLinda/concept-based-demonstration-selection>)

Recorded evaluation configuration: {"LLM":"GPT2-l"}. This record does not assert independent reproduction.

### Random

SST2 Accuracy: 84.2. Result ID: 699206813a6c3148490c1f83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

Recorded evaluation configuration: {"LLM":"GPT3-c"}. This record does not assert independent reproduction.

### Random

SST2 Accuracy: 78.5. Result ID: 699206813a6c3148490c1f85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

Recorded evaluation configuration: {"LLM":"GPT-J"}. This record does not assert independent reproduction.

### Random

SST2 Accuracy: 77.1. Result ID: 699206813a6c3148490c1f81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

Recorded evaluation configuration: {"LLM":"GPT2-l"}. This record does not assert independent reproduction.

### Demonstration Selection Algorithm

SST2 Accuracy: 74.2. Result ID: 699206813a6c3148490c1f88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Implementation](<https://github.com/WANGXinyiLinda/concept-based-demonstration-selection>)

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

### Random

SST2 Accuracy: 72.4. Result ID: 699206813a6c3148490c1f87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

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

### Demonstration Selection Algorithm

SST2 Accuracy: 60.5. Result ID: 699206813a6c3148490c1f8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Implementation](<https://github.com/WANGXinyiLinda/concept-based-demonstration-selection>)

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

### Random

SST2 Accuracy: 57.7. Result ID: 699206813a6c3148490c1f89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

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

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