# Information Analysis and Processing on MARS Overall (Evaluation Set)

Source: [Information Analysis and Processing on MARS Overall (Evaluation Set)](<https://www.sota2.com/research/sota/information-analysis-and-processing-on-mars-overall-evaluation-set>)

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

Data updated: 2026-04-08T09:14:18.234Z

Evaluation of model performance on the MARS Overall Evaluation Set for Information Analysis and Processing capabilities, measured using Average Ranking scores derived from AI GPT-5 and Expert sampling comparisons.

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 | Information Analysis and Processing |
| Dataset (including any stated split) | MARS Overall (Evaluation Set) |
| Metric | Average Ranking (AI GPT-5) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 11 of 11 |
| 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 Ranking (AI GPT-5)](<https://www.sota2.com/research/sota/information-analysis-and-processing-on-mars-overall-evaluation-set.md?metric=Average%20Ranking%20(AI%20GPT-5)>): Lower is better; unit: SCALAR.

- [Average Ranking (Experts sampling)](<https://www.sota2.com/research/sota/information-analysis-and-processing-on-mars-overall-evaluation-set.md?metric=Average%20Ranking%20(Experts%20sampling)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Average Ranking (AI GPT-5) | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 1.93 | Not recorded | 690988883ef7ccd74e5e5cef |
| Qwen3-235B-A | 2.77 | Not recorded | 690988883ef7ccd74e5e5cef |
| Llama-Vision | 5.23 | Not recorded | 690988883ef7ccd74e5e5cef |
| Llama-3.2-11B | 5.77 | Not recorded | 690988883ef7ccd74e5e5cef |
| Llama-4-Scout | 5.77 | Not recorded | 690988883ef7ccd74e5e5cef |
| Qwen-VL | 6.18 | Not recorded | 690988883ef7ccd74e5e5cef |
| Llama-3.2-90B | 6.77 | Not recorded | 690988883ef7ccd74e5e5cef |
| GPT-oss | 6.8 | Not recorded | 690988883ef7ccd74e5e5cef |
| LLaVA-1.5 | 8.03 | Not recorded | 690988883ef7ccd74e5e5cef |
| Qwen2-VL | 8.12 | Not recorded | 690988883ef7ccd74e5e5cef |
| Qwen2.5-VL | 8.43 | Not recorded | 690988883ef7ccd74e5e5cef |

### Ours

Average Ranking (AI GPT-5): 1.93. Result ID: 69d61c5847f34ce924bee7c6.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"1800B"}. This record does not assert independent reproduction.

### Qwen3-235B-A

Average Ranking (AI GPT-5): 2.77. Result ID: 69d61c5847f34ce924bee7c4.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"22B"}. This record does not assert independent reproduction.

### Llama-Vision

Average Ranking (AI GPT-5): 5.23. Result ID: 69d61c5847f34ce924bee7bd.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"11B"}. This record does not assert independent reproduction.

### Llama-3.2-11B

Average Ranking (AI GPT-5): 5.77. Result ID: 69d61c5847f34ce924bee7be.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"11B"}. This record does not assert independent reproduction.

### Llama-4-Scout

Average Ranking (AI GPT-5): 5.77. Result ID: 69d61c5847f34ce924bee7c0.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"17B"}. This record does not assert independent reproduction.

### Qwen-VL

Average Ranking (AI GPT-5): 6.18. Result ID: 69d61c5847f34ce924bee7c1.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

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

### Llama-3.2-90B

Average Ranking (AI GPT-5): 6.77. Result ID: 69d61c5847f34ce924bee7bf.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"90B"}. This record does not assert independent reproduction.

### GPT-oss

Average Ranking (AI GPT-5): 6.8. Result ID: 69d61c5847f34ce924bee7c5.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"20B"}. This record does not assert independent reproduction.

### LLaVA-1.5

Average Ranking (AI GPT-5): 8.03. Result ID: 69d61c5847f34ce924bee7bc.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

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

### Qwen2-VL

Average Ranking (AI GPT-5): 8.12. Result ID: 69d61c5847f34ce924bee7c2.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"72B"}. This record does not assert independent reproduction.

### Qwen2.5-VL

Average Ranking (AI GPT-5): 8.43. Result ID: 69d61c5847f34ce924bee7c3.

[Reporting paper](<https://www.sota2.com/research/paper/690988883ef7ccd74e5e5cef.md>)

Recorded evaluation configuration: {"Param.":"72B"}. This record does not assert independent reproduction.

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