# Kill Entities on MCU

Source: [Kill Entities on MCU](<https://www.sota2.com/research/sota/kill-entities-on-mcu>)

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

Data updated: 2026-02-26T05:58:02.092Z

Evaluation of model performance on the Kill Entities task using the MCU dataset, reporting success rates for specific entities like Pig, Cow, and Sheep.

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 | Kill Entities |
| Dataset (including any stated split) | MCU |
| Metric | Pig Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Pig Success Rate](<https://www.sota2.com/research/sota/kill-entities-on-mcu.md?metric=Pig%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Cow Success Rate](<https://www.sota2.com/research/sota/kill-entities-on-mcu.md?metric=Cow%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Sheep Success Rate](<https://www.sota2.com/research/sota/kill-entities-on-mcu.md?metric=Sheep%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/kill-entities-on-mcu.md?metric=Average%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pig Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2-VL (IL) | 97 | Not recorded | 68fa7b3e1e209131cea8747c |
| JARVIS-VLA-Qwen2 | 97 | Not recorded | 68fa7b3e1e209131cea8747c |
| Qwen2-VL (raw) | 93 | Not recorded | 68fa7b3e1e209131cea8747c |
| VPT-BC | 55 | Not recorded | 68fa7b3e1e209131cea8747c |
| GROOT | 50 | Not recorded | 68fa7b3e1e209131cea8747c |
| VPT-RL | 35 | Not recorded | 68fa7b3e1e209131cea8747c |
| STEVE-1 | 30 | Not recorded | 68fa7b3e1e209131cea8747c |
| MineDreamer | 30 | Not recorded | 68fa7b3e1e209131cea8747c |

### Qwen2-VL (IL)

Pig Success Rate: 97. Result ID: 698b83687a967eddb76f3991.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

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

### JARVIS-VLA-Qwen2

Pig Success Rate: 97. Result ID: 698b83687a967eddb76f3992.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Implementation](<https://craftjarvis.github.io/JarvisVLA>)

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

### Qwen2-VL (raw)

Pig Success Rate: 93. Result ID: 698b83687a967eddb76f3990.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

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

### VPT-BC

Pig Success Rate: 55. Result ID: 698b83687a967eddb76f398b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd61e209131cea361bb.md>)

Recorded evaluation configuration: {"Model Size":"248M"}. This record does not assert independent reproduction.

### GROOT

Pig Success Rate: 50. Result ID: 698b83687a967eddb76f398e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71471e209131cea50582.md>)

Recorded evaluation configuration: {"Model Size":"248M"}. This record does not assert independent reproduction.

### VPT-RL

Pig Success Rate: 35. Result ID: 698b83687a967eddb76f398c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd61e209131cea361bb.md>)

Recorded evaluation configuration: {"Model Size":"248M"}. This record does not assert independent reproduction.

### STEVE-1

Pig Success Rate: 30. Result ID: 698b83687a967eddb76f398d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa721b1e209131cea54867.md>)

Recorded evaluation configuration: {"Model Size":"248M"}. This record does not assert independent reproduction.

### MineDreamer

Pig Success Rate: 30. Result ID: 698b83687a967eddb76f398f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b3e1e209131cea8747c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa728f1e209131cea570e9.md>)

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

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