# Autonomous Driving Reasoning on DriveLM 25% Token Retention

Source: [Autonomous Driving Reasoning on DriveLM 25% Token Retention](<https://www.sota2.com/research/sota/autonomous-driving-reasoning-on-drivelm-25-percent-token-retention>)

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

Data updated: 2026-04-23T08:08:56.161Z

Evaluation of autonomous driving reasoning capabilities using the DriveLM dataset restricted to 25% token retention.

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 | Autonomous Driving Reasoning |
| Dataset (including any stated split) | DriveLM 25% Token Retention |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/autonomous-driving-reasoning-on-drivelm-25-percent-token-retention.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [ChatGPT Score](<https://www.sota2.com/research/sota/autonomous-driving-reasoning-on-drivelm-25-percent-token-retention.md?metric=ChatGPT%20Score>): Higher is better; unit: PERCENT.

- [Language Model Score](<https://www.sota2.com/research/sota/autonomous-driving-reasoning-on-drivelm-25-percent-token-retention.md?metric=Language%20Model%20Score>): Higher is better; unit: PERCENT.

- [Match Score](<https://www.sota2.com/research/sota/autonomous-driving-reasoning-on-drivelm-25-percent-token-retention.md?metric=Match%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/autonomous-driving-reasoning-on-drivelm-25-percent-token-retention.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DriveMM (Vanilla) | 81.23 | Not recorded | 69e85ba27d0172140ec80f94 |
| ST-Prune | 81.1 | Not recorded | 69e85ba27d0172140ec80f94 |
| PACT | 78.26 | Not recorded | 69e85ba27d0172140ec80f94 |
| DivPrune | 76.72 | Not recorded | 69e85ba27d0172140ec80f94 |
| VisPruner | 75.84 | Not recorded | 69e85ba27d0172140ec80f94 |

### DriveMM (Vanilla)

Accuracy: 81.23. Result ID: 69e9d39747f34ce924d0d94a.

[Reporting paper](<https://www.sota2.com/research/paper/69e85ba27d0172140ec80f94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a741e209131cea835a8.md>)

Recorded evaluation configuration: {"Token Retention Rate":"Full Tokens"}. This record does not assert independent reproduction.

### ST-Prune

Accuracy: 81.1. Result ID: 69e9d39747f34ce924d0d94e.

[Reporting paper](<https://www.sota2.com/research/paper/69e85ba27d0172140ec80f94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85ba27d0172140ec80f94.md>)

Recorded evaluation configuration: {"Token Retention Rate":"25%"}. This record does not assert independent reproduction.

### PACT

Accuracy: 78.26. Result ID: 69e9d39747f34ce924d0d94d.

[Reporting paper](<https://www.sota2.com/research/paper/69e85ba27d0172140ec80f94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ec1e209131cea76055.md>)

Recorded evaluation configuration: {"Token Retention Rate":"25%","Venue":"CVPR 2025"}. This record does not assert independent reproduction.

### DivPrune

Accuracy: 76.72. Result ID: 69e9d39747f34ce924d0d94c.

[Reporting paper](<https://www.sota2.com/research/paper/69e85ba27d0172140ec80f94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c41e209131cea7532a.md>)

Recorded evaluation configuration: {"Token Retention Rate":"25%","Venue":"CVPR 2025"}. This record does not assert independent reproduction.

### VisPruner

Accuracy: 75.84. Result ID: 69e9d39747f34ce924d0d94b.

[Reporting paper](<https://www.sota2.com/research/paper/69e85ba27d0172140ec80f94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78741e209131cea786bf.md>)

Recorded evaluation configuration: {"Token Retention Rate":"25%","Venue":"ICCV 2025"}. This record does not assert independent reproduction.

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