# Multimodal Instruction Following on ViSiT-Bench Sept. 27th, 2023 (Leaderboard)

Source: [Multimodal Instruction Following on ViSiT-Bench Sept. 27th, 2023 (Leaderboard)](<https://www.sota2.com/research/sota/multimodal-instruction-following-on-visit-bench-sept-27th-2023-leaderboard>)

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

Data updated: 2026-02-26T05:41:31.528Z

Evaluation of model performance on following multimodal instructions using the ViSiT-Bench dataset as of September 27th, 2023, typically measured using ELO ratings.

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 | Multimodal Instruction Following |
| Dataset (including any stated split) | ViSiT-Bench Sept. 27th, 2023 (Leaderboard) |
| Metric | ELO |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [ELO](<https://www.sota2.com/research/sota/multimodal-instruction-following-on-visit-bench-sept-27th-2023-leaderboard.md?metric=ELO>): Higher is better; unit: SCALAR.

- [Matches](<https://www.sota2.com/research/sota/multimodal-instruction-following-on-visit-bench-sept-27th-2023-leaderboard.md?metric=Matches>): Higher is better; unit: SCALAR.

- [Win](<https://www.sota2.com/research/sota/multimodal-instruction-following-on-visit-bench-sept-27th-2023-leaderboard.md?metric=Win>): Higher is better; unit: SCALAR.

- [Num Ratings](<https://www.sota2.com/research/sota/multimodal-instruction-following-on-visit-bench-sept-27th-2023-leaderboard.md?metric=Num%20Ratings>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ELO | Result date | Report paper |
| --- | --- | --- | --- |
| Human Reference | 1382 | Not recorded | 68fa71201e209131cea4f4e0 |
| LLaVA-Plus | 1203 | Not recorded | 68fa71201e209131cea4f4e0 |
| LLaVA | 1095 | Not recorded | 68fa71201e209131cea4f4e0 |
| mPLUG-Owl | 1087 | Not recorded | 68fa71201e209131cea4f4e0 |
| LlamaAdapter-v2 | 1066 | Not recorded | 68fa71201e209131cea4f4e0 |
| Lynx | 1037 | Not recorded | 68fa71201e209131cea4f4e0 |
| Idefics | 1020 | Not recorded | 68fa71201e209131cea4f4e0 |
| InstructBLIP | 1000 | Not recorded | 68fa71201e209131cea4f4e0 |
| Otter | 962 | Not recorded | 68fa71201e209131cea4f4e0 |
| Visual GPT | 941 | Not recorded | 68fa71201e209131cea4f4e0 |
| MiniGPT-4 | 926 | Not recorded | 68fa71201e209131cea4f4e0 |
| Octopus V2 | 925 | Not recorded | 68fa71201e209131cea4f4e0 |
| OpenFlamingo V1 | 851 | Not recorded | 68fa71201e209131cea4f4e0 |
| PandaGPT | 775 | Not recorded | 68fa71201e209131cea4f4e0 |
| MultimodalGPT | 731 | Not recorded | 68fa71201e209131cea4f4e0 |

### Human Reference

ELO: 1382. Result ID: 6991b4c33a6c3148490a0d65.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

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

### LLaVA-Plus

ELO: 1203. Result ID: 6991b4c33a6c3148490a0d66.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Implementation](<https://llava-vl.github.io/llava-plus/>)

Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction.

### LLaVA

ELO: 1095. Result ID: 6991b4c33a6c3148490a0d67.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction.

### mPLUG-Owl

ELO: 1087. Result ID: 6991b4c33a6c3148490a0d68.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

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

### LlamaAdapter-v2

ELO: 1066. Result ID: 6991b4c33a6c3148490a0d69.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f331e209131cea4463a.md>)

[Implementation](<https://github.com/ZrrSkywalker/LLaMA-Adapter>)

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

### Lynx

ELO: 1037. Result ID: 6991b4c33a6c3148490a0d6a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction.

### Idefics

ELO: 1020. Result ID: 6991b4c33a6c3148490a0d6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

Recorded evaluation configuration: {"Model Size":"9B"}. This record does not assert independent reproduction.

### InstructBLIP

ELO: 1000. Result ID: 6991b4c33a6c3148490a0d6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea47021.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/instructblip>)

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

### Otter

ELO: 962. Result ID: 6991b4c33a6c3148490a0d6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a411e209131cea81f51.md>)

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

### Visual GPT

ELO: 941. Result ID: 6991b4c33a6c3148490a0d6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb21e209131cea4185c.md>)

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

### MiniGPT-4

ELO: 926. Result ID: 6991b4c33a6c3148490a0d6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70bd1e209131cea4cf90.md>)

[Implementation](<https://minigpt-4.github.io/>)

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

### Octopus V2

ELO: 925. Result ID: 6991b4c33a6c3148490a0d70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

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

### OpenFlamingo V1

ELO: 851. Result ID: 6991b4c33a6c3148490a0d71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

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

### PandaGPT

ELO: 775. Result ID: 6991b4c33a6c3148490a0d72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction.

### MultimodalGPT

ELO: 731. Result ID: 6991b4c33a6c3148490a0d73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.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.
