# General Language Understanding and Reasoning on Academic Benchmarks (test)

Source: [General Language Understanding and Reasoning on Academic Benchmarks (test)](<https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-academic-benchmarks-test>)

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

Data updated: 2026-02-26T05:35:49.040Z

Evaluation of model performance across general language understanding and reasoning capabilities using the test split of the Academic Benchmarks suite, covering domains such as MMLU, coding, and mathematics.

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 | General Language Understanding and Reasoning |
| Dataset (including any stated split) | Academic Benchmarks (test) |
| Metric | Average Score |
| Unit | PERCENT |
| Direction | Higher 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

- [Average Score](<https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-academic-benchmarks-test.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

- [Code Score](<https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-academic-benchmarks-test.md?metric=Code%20Score>): Higher is better; unit: PERCENT.

- [Math Score](<https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-academic-benchmarks-test.md?metric=Math%20Score>): Higher is better; unit: PERCENT.

- [CR Score](<https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-academic-benchmarks-test.md?metric=CR%20Score>): Higher is better; unit: PERCENT.

- [WK Score](<https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-academic-benchmarks-test.md?metric=WK%20Score>): Higher is better; unit: PERCENT.

- [MMLU Score](<https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-academic-benchmarks-test.md?metric=MMLU%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Score | Result date | Report paper |
| --- | --- | --- | --- |
| Camelidae-8x34B-pro | 59.9 | Not recorded | 68fa74f81e209131cea64faa |
| Camelidae-8x34B | 59.3 | Not recorded | 68fa74f81e209131cea64faa |
| SUSChat-34B | 53.3 | Not recorded | 68fa74f81e209131cea64faa |
| Yi-34B-Chat | 51.8 | Not recorded | 68fa74f81e209131cea64faa |
| Camelidae-8x13B | 46.5 | Not recorded | 68fa74f81e209131cea64faa |
| Llama2-13B-Chat | 41.8 | Not recorded | 68fa74f81e209131cea64faa |
| Camelidae-8x7B | 39.9 | Not recorded | 68fa74f81e209131cea64faa |
| Vicuna-13B | 39.9 | Not recorded | 68fa74f81e209131cea64faa |
| Llama2-7B-Chat | 35.4 | Not recorded | 68fa74f81e209131cea64faa |
| Vicuna-7B | 34 | Not recorded | 68fa74f81e209131cea64faa |

### Camelidae-8x34B-pro

Average Score: 59.9. Result ID: 69936d533a6c31484915dcc3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Implementation](<https://github.com/wuhy68/Parameter-Efficient-MoE>)

Recorded evaluation configuration: {"#Params":"38B"}. This record does not assert independent reproduction.

### Camelidae-8x34B

Average Score: 59.3. Result ID: 69936d533a6c31484915dcc2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Implementation](<https://github.com/wuhy68/Parameter-Efficient-MoE>)

Recorded evaluation configuration: {"#Params":"38B"}. This record does not assert independent reproduction.

### SUSChat-34B

Average Score: 53.3. Result ID: 69936d533a6c31484915dcc1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

Recorded evaluation configuration: {"#Params":"34B"}. This record does not assert independent reproduction.

### Yi-34B-Chat

Average Score: 51.8. Result ID: 69936d533a6c31484915dcc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

Recorded evaluation configuration: {"#Params":"34B"}. This record does not assert independent reproduction.

### Camelidae-8x13B

Average Score: 46.5. Result ID: 69936d533a6c31484915dcbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Implementation](<https://github.com/wuhy68/Parameter-Efficient-MoE>)

Recorded evaluation configuration: {"#Params":"15B"}. This record does not assert independent reproduction.

### Llama2-13B-Chat

Average Score: 41.8. Result ID: 69936d533a6c31484915dcbd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"#Params":"13B"}. This record does not assert independent reproduction.

### Camelidae-8x7B

Average Score: 39.9. Result ID: 69936d533a6c31484915dcbc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Implementation](<https://github.com/wuhy68/Parameter-Efficient-MoE>)

Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction.

### Vicuna-13B

Average Score: 39.9. Result ID: 69936d533a6c31484915dcbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71aa1e209131cea526df.md>)

[Implementation](<https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge>)

Recorded evaluation configuration: {"#Params":"13B"}. This record does not assert independent reproduction.

### Llama2-7B-Chat

Average Score: 35.4. Result ID: 69936d533a6c31484915dcba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"#Params":"7B"}. This record does not assert independent reproduction.

### Vicuna-7B

Average Score: 34. Result ID: 69936d533a6c31484915dcbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64faa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71aa1e209131cea526df.md>)

[Implementation](<https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge>)

Recorded evaluation configuration: {"#Params":"7B"}. This record does not assert independent reproduction.

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