# Counting on Emoji-Count

Source: [Counting on Emoji-Count](<https://www.sota2.com/research/sota/counting-on-emoji-count>)

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

Data updated: 2026-02-26T05:49:20.642Z

Evaluation of model performance for counting tasks using the Emoji-Count dataset, measured by Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).

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 | Counting |
| Dataset (including any stated split) | Emoji-Count |
| Metric | MAE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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

- [MAE](<https://www.sota2.com/research/sota/counting-on-emoji-count.md?metric=MAE>): Lower is better; unit: SCALAR.

- [Delta MAE](<https://www.sota2.com/research/sota/counting-on-emoji-count.md?metric=Delta%20MAE>): Lower is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/counting-on-emoji-count.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [Delta RMSE](<https://www.sota2.com/research/sota/counting-on-emoji-count.md?metric=Delta%20RMSE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MAE | Result date | Report paper |
| --- | --- | --- | --- |
| LVLM-Count | 16.16 | Not recorded | 68fa78f21e209131cea7b607 |
| LVLM-Count | 16.57 | Not recorded | 68fa78f21e209131cea7b607 |
| Gemma 3 27B | 21.39 | Not recorded | 68fa78f21e209131cea7b607 |
| GPT-4o | 23.57 | Not recorded | 68fa78f21e209131cea7b607 |
| LVLM-Count | 24.43 | Not recorded | 68fa78f21e209131cea7b607 |
| TFOC | 64.64 | Not recorded | 68fa78f21e209131cea7b607 |
| Qwen2 VL 72B AWQ | 78.05 | Not recorded | 68fa78f21e209131cea7b607 |
| CountGD | 137.93 | Not recorded | 68fa78f21e209131cea7b607 |
| GroundingREC | 143.22 | Not recorded | 68fa78f21e209131cea7b607 |
| DAVEprm | 198.99 | Not recorded | 68fa78f21e209131cea7b607 |

### LVLM-Count

MAE: 16.16. Result ID: 699a89ac5698665ec413ca9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

Recorded evaluation configuration: {"Base LVLM":"Gemma 3 27B"}. This record does not assert independent reproduction.

### LVLM-Count

MAE: 16.57. Result ID: 699a89ac5698665ec413ca9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

Recorded evaluation configuration: {"Base LVLM":"GPT-4o"}. This record does not assert independent reproduction.

### Gemma 3 27B

MAE: 21.39. Result ID: 699a89ac5698665ec413ca9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o

MAE: 23.57. Result ID: 699a89ac5698665ec413ca9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LVLM-Count

MAE: 24.43. Result ID: 699a89ac5698665ec413caa0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

Recorded evaluation configuration: {"Base LVLM":"Qwen2 VL 72B AWQ"}. This record does not assert independent reproduction.

### TFOC

MAE: 64.64. Result ID: 699a89ac5698665ec413ca97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70721e209131cea4b0a7.md>)

[Implementation](<https://github.com/shizenglin/training-free-object-counter>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen2 VL 72B AWQ

MAE: 78.05. Result ID: 699a89ac5698665ec413ca9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea6378d.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CountGD

MAE: 137.93. Result ID: 699a89ac5698665ec413ca99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77581e209131cea728c0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GroundingREC

MAE: 143.22. Result ID: 699a89ac5698665ec413ca9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DAVEprm

MAE: 198.99. Result ID: 699a89ac5698665ec413ca98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b607.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73091e209131cea59feb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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