# Part-level Contact MCQ on PARSE-10K (test)

Source: [Part-level Contact MCQ on PARSE-10K (test)](<https://www.sota2.com/research/sota/part-level-contact-mcq-on-parse-10k-test>)

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

Data updated: 2026-03-10T11:00:22.668Z

Evaluation of model performance on the test split of the PARSE-10K dataset for Part-level Contact Multiple Choice Question (MCQ) evaluation, measured using Accuracy.

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 | Part-level Contact MCQ |
| Dataset (including any stated split) | PARSE-10K (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/part-level-contact-mcq-on-parse-10k-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 86.2 | Not recorded | 69afa58c2d603e6de3e43ad5 |
| Gemini-2.5-Pro | 75.6 | Not recorded | 69afa58c2d603e6de3e43ad5 |
| GPT-5 | 75.2 | Not recorded | 69afa58c2d603e6de3e43ad5 |
| Claude-Opus-4 | 73.2 | Not recorded | 69afa58c2d603e6de3e43ad5 |
| Qwen3-VL | 60.4 | Not recorded | 69afa58c2d603e6de3e43ad5 |
| Robobrain2.0 | 37.2 | Not recorded | 69afa58c2d603e6de3e43ad5 |

### Ours

Accuracy: 86.2. Result ID: 69aff9b76dbb7075b9593f29.

[Reporting paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad5.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Fine-tuned","Base Model":"Qwen3-VL"}. This record does not assert independent reproduction.

### Gemini-2.5-Pro

Accuracy: 75.6. Result ID: 69aff9b76dbb7075b9593f25.

[Reporting paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction.

### GPT-5

Accuracy: 75.2. Result ID: 69aff9b76dbb7075b9593f24.

[Reporting paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad5.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Claude-Opus-4

Accuracy: 73.2. Result ID: 69aff9b76dbb7075b9593f26.

[Reporting paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad5.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Qwen3-VL

Accuracy: 60.4. Result ID: 69aff9b76dbb7075b9593f28.

[Reporting paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad5.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Robobrain2.0

Accuracy: 37.2. Result ID: 69aff9b76dbb7075b9593f27.

[Reporting paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b4d1e209131cea87a54.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction.

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