# Intent reasoning on Real-world intent reasoning 88 samples (test)

Source: [Intent reasoning on Real-world intent reasoning 88 samples (test)](<https://www.sota2.com/research/sota/intent-reasoning-on-real-world-intent-reasoning-88-samples-test>)

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

Data updated: 2026-05-22T09:56:55.353Z

Evaluation of model performance on the test split of the Real-world intent reasoning dataset (88 samples), focusing on intent reasoning capabilities, measured by Accuracy and Progress Score.

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 | Intent reasoning |
| Dataset (including any stated split) | Real-world intent reasoning 88 samples (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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/intent-reasoning-on-real-world-intent-reasoning-88-samples-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Progress Score](<https://www.sota2.com/research/sota/intent-reasoning-on-real-world-intent-reasoning-88-samples-test.md?metric=Progress%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GesVLA (VLMint) | 94.3 | Not recorded | 6a0fe347f984739ed673a09c |
| Baseline-2 (geometric pipeline) | 59.1 | Not recorded | 6a0fe347f984739ed673a09c |
| Baseline-1 (prompted MLLM) | 38.6 | Not recorded | 6a0fe347f984739ed673a09c |

### GesVLA (VLMint)

Accuracy: 94.3. Result ID: 6a1027fefbc373592c09a217.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe347f984739ed673a09c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe347f984739ed673a09c.md>)

Recorded evaluation configuration: {"Module":"VLMint"}. This record does not assert independent reproduction.

### Baseline-2 (geometric pipeline)

Accuracy: 59.1. Result ID: 6a1027fefbc373592c09a216.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe347f984739ed673a09c.md>)

Recorded evaluation configuration: {"Pipeline Components":"MediaPipe, GroundingDINO, DepthAnythingV2"}. This record does not assert independent reproduction.

### Baseline-1 (prompted MLLM)

Accuracy: 38.6. Result ID: 6a1027fefbc373592c09a215.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe347f984739ed673a09c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3.5-plus"}. This record does not assert independent reproduction.

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