# Question Answering on TruthfulQA (Macro-F1)

Source: [Question Answering on TruthfulQA (Macro-F1)](<https://www.sota2.com/research/sota/question-answering-on-truthfulqa-macro-f1>)

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

Data updated: 2026-05-27T10:31:14.463Z

Evaluation of model performance on the TruthfulQA dataset using the Macro-F1 metric for question answering.

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 | Question-answering |
| Dataset (including any stated split) | TruthfulQA |
| Metric | Macro-F1 |
| 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

- [Macro-F1](<https://www.sota2.com/research/sota/question-answering-on-truthfulqa-macro-f1.md?metric=Macro-F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Macro-F1 | Result date | Report paper |
| --- | --- | --- | --- |
| MATCHA | 61.08 | Not recorded | 6a167adadbd7150506f80321 |
| BLEURT | 56.03 | Not recorded | 6a167adadbd7150506f80321 |
| METEOR | 55.2 | Not recorded | 6a167adadbd7150506f80321 |
| R1-F1 | 55.04 | Not recorded | 6a167adadbd7150506f80321 |
| RL-F1 | 51.53 | Not recorded | 6a167adadbd7150506f80321 |
| R2-F1 | 44.29 | Not recorded | 6a167adadbd7150506f80321 |
| SimCSE | 34.65 | Not recorded | 6a167adadbd7150506f80321 |
| EmbSim | 33.95 | Not recorded | 6a167adadbd7150506f80321 |
| BERTScore | 33.33 | Not recorded | 6a167adadbd7150506f80321 |

### MATCHA

Macro-F1: 61.08. Result ID: 6a16c652fbc373592c10953d.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### BLEURT

Macro-F1: 56.03. Result ID: 6a16c652fbc373592c10953b.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67961e209131cea173db.md>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### METEOR

Macro-F1: 55.2. Result ID: 6a16c652fbc373592c109538.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### R1-F1

Macro-F1: 55.04. Result ID: 6a16c652fbc373592c109535.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### RL-F1

Macro-F1: 51.53. Result ID: 6a16c652fbc373592c109537.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### R2-F1

Macro-F1: 44.29. Result ID: 6a16c652fbc373592c109536.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### SimCSE

Macro-F1: 34.65. Result ID: 6a16c652fbc373592c10953c.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9c1e209131cea34e2c.md>)

[Implementation](<https://github.com/princeton-nlp/SimCSE>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### EmbSim

Macro-F1: 33.95. Result ID: 6a16c652fbc373592c109539.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66441e209131cea0f5ab.md>)

[Implementation](<https://github.com/UKPLab/sentence-transformers>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

### BERTScore

Macro-F1: 33.33. Result ID: 6a16c652fbc373592c10953a.

[Reporting paper](<https://www.sota2.com/research/paper/6a167adadbd7150506f80321.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67171e209131cea140d5.md>)

Recorded evaluation configuration: {"Threshold":"fixed midpoint threshold"}. This record does not assert independent reproduction.

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