# Intent Grasping on IntentGrasp Gem Set

Source: [Intent Grasping on IntentGrasp Gem Set](<https://www.sota2.com/research/sota/intent-grasping-on-intentgrasp-gem-set>)

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

Data updated: 2026-05-11T07:31:28.647Z

Evaluation of Intent Grasping performance on the IntentGrasp Gem Set dataset, reporting metrics such as F1 score, Average, and Standard Deviation.

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 Grasping |
| Dataset (including any stated split) | IntentGrasp Gem Set |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 45 of 45 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/intent-grasping-on-intentgrasp-gem-set.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/intent-grasping-on-intentgrasp-gem-set.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

- [Standard Deviation](<https://www.sota2.com/research/sota/intent-grasping-on-intentgrasp-gem-set.md?metric=Standard%20Deviation>): Lower is better; unit: SCALAR.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Gemini 3-Flash | 0.2499 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3-Flash | 0.2498 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3-Flash | 0.2495 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3-Flash | 0.2375 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Pro | 0.2214 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Pro | 0.2184 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Pro | 0.2154 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Pro | 0.2051 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Opus-4.7 | 0.1801 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Opus-4.7 | 0.1623 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Opus-4.7 | 0.1614 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Opus-4.7 | 0.1581 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4 | 0.1275 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Sonnet-4.6 | 0.1238 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Flash-Lite | 0.1212 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4 | 0.1189 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Sonnet-4.6 | 0.1184 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Sonnet-4.6 | 0.1174 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Flash-Lite | 0.1167 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Flash-Lite | 0.1166 | Not recorded | 6a01628adbc836b87d823071 |
| Gemini 3.1-Flash-Lite | 0.1162 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4 | 0.114 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4 | 0.1079 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-nano | 0.0898 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-nano | 0.0863 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-nano | 0.0862 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-mini | 0.0855 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-nano | 0.0847 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Sonnet-4.6 | 0.0766 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Haiku-4.5 | 0.0723 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-mini | 0.0688 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-mini | 0.067 | Not recorded | 6a01628adbc836b87d823071 |
| GPT 5.4-mini | 0.0617 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Haiku-4.5 | 0.0585 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Haiku-4.5 | 0.054 | Not recorded | 6a01628adbc836b87d823071 |
| Claude Haiku-4.5 | 0.0454 | Not recorded | 6a01628adbc836b87d823071 |

### Gemini 3-Flash

F1 Score: 0.2499. Result ID: 6a0185bb47f34ce924e2ffb3.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### Gemini 3-Flash

F1 Score: 0.2498. Result ID: 6a0185bb47f34ce924e2ffb4.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

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

### Gemini 3-Flash

F1 Score: 0.2495. Result ID: 6a0185bb47f34ce924e2ffb5.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### Gemini 3-Flash

F1 Score: 0.2375. Result ID: 6a0185bb47f34ce924e2ffb6.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### Gemini 3.1-Pro

F1 Score: 0.2214. Result ID: 6a0185bb47f34ce924e2ffaf.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

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

### Gemini 3.1-Pro

F1 Score: 0.2184. Result ID: 6a0185bb47f34ce924e2ffb0.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### Gemini 3.1-Pro

F1 Score: 0.2154. Result ID: 6a0185bb47f34ce924e2ffae.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### Gemini 3.1-Pro

F1 Score: 0.2051. Result ID: 6a0185bb47f34ce924e2ffb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### Claude Opus-4.7

F1 Score: 0.1801. Result ID: 6a0185bb47f34ce924e2ffbf.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### Claude Opus-4.7

F1 Score: 0.1623. Result ID: 6a0185bb47f34ce924e2ffbd.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### Claude Opus-4.7

F1 Score: 0.1614. Result ID: 6a0185bb47f34ce924e2ffbe.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

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

### Claude Opus-4.7

F1 Score: 0.1581. Result ID: 6a0185bb47f34ce924e2ffc0.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### GPT 5.4

F1 Score: 0.1275. Result ID: 6a0185bb47f34ce924e2ffa1.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### Claude Sonnet-4.6

F1 Score: 0.1238. Result ID: 6a0185bb47f34ce924e2ffc4.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### Gemini 3.1-Flash-Lite

F1 Score: 0.1212. Result ID: 6a0185bb47f34ce924e2ffba.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### GPT 5.4

F1 Score: 0.1189. Result ID: 6a0185bb47f34ce924e2ffa2.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### Claude Sonnet-4.6

F1 Score: 0.1184. Result ID: 6a0185bb47f34ce924e2ffc3.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

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

### Claude Sonnet-4.6

F1 Score: 0.1174. Result ID: 6a0185bb47f34ce924e2ffc5.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### Gemini 3.1-Flash-Lite

F1 Score: 0.1167. Result ID: 6a0185bb47f34ce924e2ffbb.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### Gemini 3.1-Flash-Lite

F1 Score: 0.1166. Result ID: 6a0185bb47f34ce924e2ffb8.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### Gemini 3.1-Flash-Lite

F1 Score: 0.1162. Result ID: 6a0185bb47f34ce924e2ffb9.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

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

### GPT 5.4

F1 Score: 0.114. Result ID: 6a0185bb47f34ce924e2ffa0.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

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

### GPT 5.4

F1 Score: 0.1079. Result ID: 6a0185bb47f34ce924e2ff9f.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### GPT 5.4-nano

F1 Score: 0.0898. Result ID: 6a0185bb47f34ce924e2ffab.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### GPT 5.4-nano

F1 Score: 0.0863. Result ID: 6a0185bb47f34ce924e2ffa9.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### GPT 5.4-nano

F1 Score: 0.0862. Result ID: 6a0185bb47f34ce924e2ffaa.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

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

### GPT 5.4-mini

F1 Score: 0.0855. Result ID: 6a0185bb47f34ce924e2ffa7.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### GPT 5.4-nano

F1 Score: 0.0847. Result ID: 6a0185bb47f34ce924e2ffac.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### Claude Sonnet-4.6

F1 Score: 0.0766. Result ID: 6a0185bb47f34ce924e2ffc2.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### Claude Haiku-4.5

F1 Score: 0.0723. Result ID: 6a0185bb47f34ce924e2ffc9.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### GPT 5.4-mini

F1 Score: 0.0688. Result ID: 6a0185bb47f34ce924e2ffa6.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-42"}. This record does not assert independent reproduction.

### GPT 5.4-mini

F1 Score: 0.067. Result ID: 6a0185bb47f34ce924e2ffa5.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

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

### GPT 5.4-mini

F1 Score: 0.0617. Result ID: 6a0185bb47f34ce924e2ffa4.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

### Claude Haiku-4.5

F1 Score: 0.0585. Result ID: 6a0185bb47f34ce924e2ffca.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"shuffle-365"}. This record does not assert independent reproduction.

### Claude Haiku-4.5

F1 Score: 0.054. Result ID: 6a0185bb47f34ce924e2ffc8.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

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

### Claude Haiku-4.5

F1 Score: 0.0454. Result ID: 6a0185bb47f34ce924e2ffc7.

[Reporting paper](<https://www.sota2.com/research/paper/6a01628adbc836b87d823071.md>)

Recorded evaluation configuration: {"shuffle":"no shuffle"}. This record does not assert independent reproduction.

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