# Question Answering on ARC Challenge (NLL)

Source: [Question Answering on ARC Challenge (NLL)](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-nll>)

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

Data updated: 2026-06-11T06:44:55.584Z

Evaluation of model performance on the ARC Challenge dataset for Question Answering, specifically reporting Negative Log Likelihood (NLL).

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) | ARC Challenge |
| Metric | NLL |
| Unit | SCALAR |
| Direction | Lower 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

- [NLL](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-nll.md?metric=NLL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | NLL | Result date | Report paper |
| --- | --- | --- | --- |
| PPT (Distribution) + TS | 0.47 | Not recorded | 6a28f33b90966ade919c16e2 |
| Base + TS | 0.49 | Not recorded | 6a28f33b90966ade919c16e2 |
| PPT (Distribution) | 0.51 | Not recorded | 6a28f33b90966ade919c16e2 |
| PPT (Distribution) + TS | 0.6 | Not recorded | 6a28f33b90966ade919c16e2 |
| PPT (Distribution) | 0.61 | Not recorded | 6a28f33b90966ade919c16e2 |
| Base + TS | 0.62 | Not recorded | 6a28f33b90966ade919c16e2 |
| PPT (Mean) | 0.74 | Not recorded | 6a28f33b90966ade919c16e2 |
| PPT (Mean) | 0.76 | Not recorded | 6a28f33b90966ade919c16e2 |
| Base | 0.9 | Not recorded | 6a28f33b90966ade919c16e2 |
| Base | 0.98 | Not recorded | 6a28f33b90966ade919c16e2 |

### PPT (Distribution) + TS

NLL: 0.47. Result ID: 6a2a5885fbc373592c26c707.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"QWEN2-7B","Temperature Scaling":"true"}. This record does not assert independent reproduction.

### Base + TS

NLL: 0.49. Result ID: 6a2a5885fbc373592c26c706.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff6d1.md>)

Recorded evaluation configuration: {"Backbone":"QWEN2-7B","Temperature Scaling":"true"}. This record does not assert independent reproduction.

### PPT (Distribution)

NLL: 0.51. Result ID: 6a2a5885fbc373592c26c704.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"QWEN2-7B","Temperature Scaling":"false"}. This record does not assert independent reproduction.

### PPT (Distribution) + TS

NLL: 0.6. Result ID: 6a2a5885fbc373592c26c702.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"LLAMA3-8B","Temperature Scaling":"true"}. This record does not assert independent reproduction.

### PPT (Distribution)

NLL: 0.61. Result ID: 6a2a5885fbc373592c26c6ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"LLAMA3-8B","Temperature Scaling":"false"}. This record does not assert independent reproduction.

### Base + TS

NLL: 0.62. Result ID: 6a2a5885fbc373592c26c701.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff6d1.md>)

Recorded evaluation configuration: {"Backbone":"LLAMA3-8B","Temperature Scaling":"true"}. This record does not assert independent reproduction.

### PPT (Mean)

NLL: 0.74. Result ID: 6a2a5885fbc373592c26c700.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"LLAMA3-8B","Temperature Scaling":"false"}. This record does not assert independent reproduction.

### PPT (Mean)

NLL: 0.76. Result ID: 6a2a5885fbc373592c26c705.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"QWEN2-7B","Temperature Scaling":"false"}. This record does not assert independent reproduction.

### Base

NLL: 0.9. Result ID: 6a2a5885fbc373592c26c703.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"QWEN2-7B","Temperature Scaling":"false"}. This record does not assert independent reproduction.

### Base

NLL: 0.98. Result ID: 6a2a5885fbc373592c26c6fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33b90966ade919c16e2.md>)

Recorded evaluation configuration: {"Backbone":"LLAMA3-8B","Temperature Scaling":"false"}. This record does not assert independent reproduction.

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