# Uncertainty Calibration on TQA

Source: [Uncertainty Calibration on TQA](<https://www.sota2.com/research/sota/uncertainty-calibration-on-tqa>)

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

Data updated: 2026-06-04T10:01:05.204Z

Evaluation of model uncertainty calibration performance on the TQA dataset, typically measured using metrics like Brier 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 | Uncertainty Calibration |
| Dataset (including any stated split) | TQA |
| Metric | Brier Score |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 28 of 28 |
| 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

- [Brier Score](<https://www.sota2.com/research/sota/uncertainty-calibration-on-tqa.md?metric=Brier%20Score>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Brier Score | Result date | Report paper |
| --- | --- | --- | --- |
| Clustered Self-Assessment | 0.0721 | Not recorded | 6a210692c10484bac23f01a9 |
| Clustered Self-Assessment | 0.0843 | Not recorded | 6a210692c10484bac23f01a9 |
| Clustered Self-Assessment | 0.0894 | Not recorded | 6a210692c10484bac23f01a9 |
| Clustered Self-Assessment | 0.0917 | Not recorded | 6a210692c10484bac23f01a9 |
| Clustered Self-Assessment | 0.0921 | Not recorded | 6a210692c10484bac23f01a9 |
| NSE | 0.0937 | Not recorded | 6a210692c10484bac23f01a9 |
| Clustered Self-Assessment | 0.0943 | Not recorded | 6a210692c10484bac23f01a9 |
| P(True) | 0.1172 | Not recorded | 6a210692c10484bac23f01a9 |
| Clustered Self-Assessment | 0.1183 | Not recorded | 6a210692c10484bac23f01a9 |
| NSE | 0.12 | Not recorded | 6a210692c10484bac23f01a9 |
| NSE | 0.1283 | Not recorded | 6a210692c10484bac23f01a9 |
| NSE | 0.1289 | Not recorded | 6a210692c10484bac23f01a9 |
| P(True) | 0.1315 | Not recorded | 6a210692c10484bac23f01a9 |
| NSE | 0.1342 | Not recorded | 6a210692c10484bac23f01a9 |
| P(True) | 0.1398 | Not recorded | 6a210692c10484bac23f01a9 |
| P(True) | 0.14 | Not recorded | 6a210692c10484bac23f01a9 |
| NSE | 0.1421 | Not recorded | 6a210692c10484bac23f01a9 |
| NSE | 0.158 | Not recorded | 6a210692c10484bac23f01a9 |
| Probability | 0.1674 | Not recorded | 6a210692c10484bac23f01a9 |
| P(True) | 0.1708 | Not recorded | 6a210692c10484bac23f01a9 |
| P(True) | 0.1758 | Not recorded | 6a210692c10484bac23f01a9 |
| Probability | 0.1807 | Not recorded | 6a210692c10484bac23f01a9 |
| Probability | 0.1917 | Not recorded | 6a210692c10484bac23f01a9 |
| Probability | 0.1975 | Not recorded | 6a210692c10484bac23f01a9 |
| Probability | 0.2001 | Not recorded | 6a210692c10484bac23f01a9 |
| P(True) | 0.2147 | Not recorded | 6a210692c10484bac23f01a9 |
| Probability | 0.2267 | Not recorded | 6a210692c10484bac23f01a9 |
| Probability | 0.2402 | Not recorded | 6a210692c10484bac23f01a9 |

### Clustered Self-Assessment

Brier Score: 0.0721. Result ID: 6a214cd2fbc373592c1d7740.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-27B"}. This record does not assert independent reproduction.

### Clustered Self-Assessment

Brier Score: 0.0843. Result ID: 6a214cd2fbc373592c1d773c.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-32B"}. This record does not assert independent reproduction.

### Clustered Self-Assessment

Brier Score: 0.0894. Result ID: 6a214cd2fbc373592c1d773e.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### Clustered Self-Assessment

Brier Score: 0.0917. Result ID: 6a214cd2fbc373592c1d773b.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction.

### Clustered Self-Assessment

Brier Score: 0.0921. Result ID: 6a214cd2fbc373592c1d773d.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### NSE

Brier Score: 0.0937. Result ID: 6a214cd2fbc373592c1d7755.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-27B"}. This record does not assert independent reproduction.

### Clustered Self-Assessment

Brier Score: 0.0943. Result ID: 6a214cd2fbc373592c1d773f.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-12B"}. This record does not assert independent reproduction.

### P(True)

Brier Score: 0.1172. Result ID: 6a214cd2fbc373592c1d7743.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-32B"}. This record does not assert independent reproduction.

### Clustered Self-Assessment

Brier Score: 0.1183. Result ID: 6a214cd2fbc373592c1d773a.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction.

### NSE

Brier Score: 0.12. Result ID: 6a214cd2fbc373592c1d7751.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-32B"}. This record does not assert independent reproduction.

### NSE

Brier Score: 0.1283. Result ID: 6a214cd2fbc373592c1d7752.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### NSE

Brier Score: 0.1289. Result ID: 6a214cd2fbc373592c1d7753.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### P(True)

Brier Score: 0.1315. Result ID: 6a214cd2fbc373592c1d7744.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### NSE

Brier Score: 0.1342. Result ID: 6a214cd2fbc373592c1d7750.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction.

### P(True)

Brier Score: 0.1398. Result ID: 6a214cd2fbc373592c1d7745.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### P(True)

Brier Score: 0.14. Result ID: 6a214cd2fbc373592c1d7742.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction.

### NSE

Brier Score: 0.1421. Result ID: 6a214cd2fbc373592c1d7754.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-12B"}. This record does not assert independent reproduction.

### NSE

Brier Score: 0.158. Result ID: 6a214cd2fbc373592c1d774f.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction.

### Probability

Brier Score: 0.1674. Result ID: 6a214cd2fbc373592c1d7748.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction.

### P(True)

Brier Score: 0.1708. Result ID: 6a214cd2fbc373592c1d7741.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction.

### P(True)

Brier Score: 0.1758. Result ID: 6a214cd2fbc373592c1d7747.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-27B"}. This record does not assert independent reproduction.

### Probability

Brier Score: 0.1807. Result ID: 6a214cd2fbc373592c1d774b.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### Probability

Brier Score: 0.1917. Result ID: 6a214cd2fbc373592c1d774c.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### Probability

Brier Score: 0.1975. Result ID: 6a214cd2fbc373592c1d774e.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-27B"}. This record does not assert independent reproduction.

### Probability

Brier Score: 0.2001. Result ID: 6a214cd2fbc373592c1d7749.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction.

### P(True)

Brier Score: 0.2147. Result ID: 6a214cd2fbc373592c1d7746.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-12B"}. This record does not assert independent reproduction.

### Probability

Brier Score: 0.2267. Result ID: 6a214cd2fbc373592c1d774a.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-32B"}. This record does not assert independent reproduction.

### Probability

Brier Score: 0.2402. Result ID: 6a214cd2fbc373592c1d774d.

[Reporting paper](<https://www.sota2.com/research/paper/6a210692c10484bac23f01a9.md>)

Recorded evaluation configuration: {"Backbone":"Gemma-3-12B"}. This record does not assert independent reproduction.

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