# GFLOPs per token on E2E for Natural Language Generation

Source: [GFLOPs per token on E2E for Natural Language Generation](<https://www.sota2.com/research/sota/gflops-per-token-on-e2e-for-natural-language-generation>)

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

Data updated: 2026-02-26T05:45:43.140Z

Evaluation of the computational efficiency of Natural Language Generation models on the E2E dataset, measured by GFLOPs per token.

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 | Natural Language Generation |
| Dataset (including any stated split) | E2E |
| Metric | GFLOPs per token |
| 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

- [GFLOPs per token](<https://www.sota2.com/research/sota/gflops-per-token-on-e2e-for-natural-language-generation.md?metric=GFLOPs%20per%20token>): Lower is better; unit: SCALAR.

## Recorded results

| Method | GFLOPs per token | Result date | Report paper |
| --- | --- | --- | --- |
| LTE | 4.65 | Not recorded | 68fa76221e209131cea6b680 |
| Deja Vu | 6.42 | Not recorded | 68fa76221e209131cea6b680 |
| R-LLaMA+MoE | 7.39 | Not recorded | 68fa76221e209131cea6b680 |
| Full | 12.06 | Not recorded | 68fa76221e209131cea6b680 |

### LTE

GFLOPs per token: 4.65. Result ID: 699425f03a6c3148491b6493.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76221e209131cea6b680.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76221e209131cea6b680.md>)

[Implementation](<https://github.com/haizhongzheng/LTE>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Permitted Quality Drop":"ROUGE-L \<= 0.05"}. This record does not assert independent reproduction.

### Deja Vu

GFLOPs per token: 6.42. Result ID: 699425f03a6c3148491b6491.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76221e209131cea6b680.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71081e209131cea4ec02.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Permitted Quality Drop":"ROUGE-L \<= 0.05"}. This record does not assert independent reproduction.

### R-LLaMA+MoE

GFLOPs per token: 7.39. Result ID: 699425f03a6c3148491b6492.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76221e209131cea6b680.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea32765.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Permitted Quality Drop":"ROUGE-L \<= 0.05"}. This record does not assert independent reproduction.

### Full

GFLOPs per token: 12.06. Result ID: 699425f03a6c3148491b6490.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76221e209131cea6b680.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Permitted Quality Drop":"ROUGE-L \<= 0.05"}. This record does not assert independent reproduction.

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