# Language Modeling on WikiText-2 (LLaMA-2 7B)

Source: [Language Modeling on WikiText-2 (LLaMA-2 7B)](<https://www.sota2.com/research/sota/language-modeling-on-wikitext-2-llama-2-7b>)

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

Data updated: 2026-02-26T05:55:11.036Z

Evaluation of Language Modeling performance on the WikiText-2 dataset, specifically reporting metrics for the LLaMA-2 7B model configuration.

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 | Language Modeling |
| Dataset (including any stated split) | WikiText-2 LLaMA-2 7B |
| Metric | PPL |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [PPL](<https://www.sota2.com/research/sota/language-modeling-on-wikitext-2-llama-2-7b.md?metric=PPL>): Lower is better; unit: SCALAR.

- [Degradation](<https://www.sota2.com/research/sota/language-modeling-on-wikitext-2-llama-2-7b.md?metric=Degradation>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PPL | Result date | Report paper |
| --- | --- | --- | --- |
| ANN Baseline | 5.12 | Not recorded | 697c3af7a8b01e76cc8da3ea |
| SpikeLLM | 11.85 | Not recorded | 697c3af7a8b01e76cc8da3ea |
| SpikeLLM | 14.16 | Not recorded | 697c3af7a8b01e76cc8da3ea |

### ANN Baseline

PPL: 5.12. Result ID: 6999ad775698665ec42537bf.

[Reporting paper](<https://www.sota2.com/research/paper/697c3af7a8b01e76cc8da3ea.md>)

Recorded evaluation configuration: {"Prec.":"FP32"}. This record does not assert independent reproduction.

### SpikeLLM

PPL: 11.85. Result ID: 6999ad775698665ec42537c1.

[Reporting paper](<https://www.sota2.com/research/paper/697c3af7a8b01e76cc8da3ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ed1e209131cea760de.md>)

Recorded evaluation configuration: {"Prec.":"W4A4","Ch./Steps":"4"}. This record does not assert independent reproduction.

### SpikeLLM

PPL: 14.16. Result ID: 6999ad775698665ec42537c2.

[Reporting paper](<https://www.sota2.com/research/paper/697c3af7a8b01e76cc8da3ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ed1e209131cea760de.md>)

Recorded evaluation configuration: {"Prec.":"W2A16","Ch./Steps":"4"}. This record does not assert independent reproduction.

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