# Language Modeling Downstream Evaluation on English Downstream Tasks 12 tasks

Source: [Language Modeling Downstream Evaluation on English Downstream Tasks 12 tasks](<https://www.sota2.com/research/sota/language-modeling-downstream-evaluation-on-english-downstream-tasks-12-tasks>)

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

Data updated: 2026-03-06T07:08:18.975Z

Evaluation of language model performance across 12 specific English downstream tasks, reporting granular scores for Reading Comprehension, Commonsense Reasoning, World Knowledge, and the overall average.

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 Downstream Evaluation |
| Dataset (including any stated split) | English Downstream Tasks 12 tasks |
| Metric | Reading Comprehension |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Reading Comprehension](<https://www.sota2.com/research/sota/language-modeling-downstream-evaluation-on-english-downstream-tasks-12-tasks.md?metric=Reading%20Comprehension>): Higher is better; unit: PERCENT.

- [Commonsense Reasoning](<https://www.sota2.com/research/sota/language-modeling-downstream-evaluation-on-english-downstream-tasks-12-tasks.md?metric=Commonsense%20Reasoning>): Higher is better; unit: PERCENT.

- [World Knowledge](<https://www.sota2.com/research/sota/language-modeling-downstream-evaluation-on-english-downstream-tasks-12-tasks.md?metric=World%20Knowledge>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/language-modeling-downstream-evaluation-on-english-downstream-tasks-12-tasks.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Reading Comprehension | Result date | Report paper |
| --- | --- | --- | --- |
| MuRater | 47.13 | Not recorded | 68fa79c41e209131cea7f3f5 |
| DCLM | 46 | Not recorded | 68fa79c41e209131cea7f3f5 |
| FineWeb\_Edu | 45.71 | Not recorded | 68fa79c41e209131cea7f3f5 |
| Uniform (+50% data) | 43.93 | Not recorded | 68fa79c41e209131cea7f3f5 |
| QuRater | 43.54 | Not recorded | 68fa79c41e209131cea7f3f5 |
| AskLLM | 42.83 | Not recorded | 68fa79c41e209131cea7f3f5 |

### MuRater

Reading Comprehension: 47.13. Result ID: 69aa7d106dbb7075b953be8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79c41e209131cea7f3f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79c41e209131cea7f3f5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DCLM

Reading Comprehension: 46. Result ID: 69aa7d106dbb7075b953be87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79c41e209131cea7f3f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78351e209131cea77359.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FineWeb\_Edu

Reading Comprehension: 45.71. Result ID: 69aa7d106dbb7075b953be88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79c41e209131cea7f3f5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Uniform (+50% data)

Reading Comprehension: 43.93. Result ID: 69aa7d106dbb7075b953be85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79c41e209131cea7f3f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74241e209131cea5ff51.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### QuRater

Reading Comprehension: 43.54. Result ID: 69aa7d106dbb7075b953be89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79c41e209131cea7f3f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74241e209131cea5ff51.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AskLLM

Reading Comprehension: 42.83. Result ID: 69aa7d106dbb7075b953be86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79c41e209131cea7f3f5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72401e209131cea554b8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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