# Omni-modal reasoning on OmniBench (test)

Source: [Omni-modal reasoning on OmniBench (test)](<https://www.sota2.com/research/sota/omni-modal-reasoning-on-omnibench-test>)

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

Data updated: 2026-03-24T12:44:40.744Z

Evaluation of Omni-modal reasoning capabilities on the test split of the OmniBench dataset.

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 | Omni-modal reasoning |
| Dataset (including any stated split) | OmniBench (test) |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [Score](<https://www.sota2.com/research/sota/omni-modal-reasoning-on-omnibench-test.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| ThinkOmni | 43.6 | Not recorded | 69a1251c2d603e6de3e3c643 |
| ThinkOmni | 43.5 | Not recorded | 69a1251c2d603e6de3e3c643 |
| ThinkOmni | 43.4 | Not recorded | 69a1251c2d603e6de3e3c643 |
| ThinkOmni | 43.2 | Not recorded | 69a1251c2d603e6de3e3c643 |
| Omni-R1 | 43 | Not recorded | 69a1251c2d603e6de3e3c643 |
| Omni-R1 | 43 | Not recorded | 69a1251c2d603e6de3e3c643 |
| Baichuan-Omni-1.5 | 42.9 | Not recorded | 69a1251c2d603e6de3e3c643 |
| Qwen2.5-Omni-7B | 42.1 | Not recorded | 69a1251c2d603e6de3e3c643 |
| HumanOmniV2 | 41.9 | Not recorded | 69a1251c2d603e6de3e3c643 |
| ThinkOmni | 39.9 | Not recorded | 69a1251c2d603e6de3e3c643 |
| ThinkOmni | 39.5 | Not recorded | 69a1251c2d603e6de3e3c643 |
| Qwen2.5-Omni-3B | 37.5 | Not recorded | 69a1251c2d603e6de3e3c643 |

### ThinkOmni

Score: 43.6. Result ID: 69c2862247f34ce924aa872e.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Omni-7B","LRM Guide":"Qwen3"}. This record does not assert independent reproduction.

### ThinkOmni

Score: 43.5. Result ID: 69c2862247f34ce924aa8730.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

Recorded evaluation configuration: {"Base Model":"Omni-R1-7B","LRM Guide":"DeepSeek"}. This record does not assert independent reproduction.

### ThinkOmni

Score: 43.4. Result ID: 69c2862247f34ce924aa8731.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

Recorded evaluation configuration: {"Base Model":"Omni-R1-7B","LRM Guide":"Qwen3"}. This record does not assert independent reproduction.

### ThinkOmni

Score: 43.2. Result ID: 69c2862247f34ce924aa872d.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Omni-7B","LRM Guide":"DeepSeek"}. This record does not assert independent reproduction.

### Omni-R1

Score: 43. Result ID: 69c2862247f34ce924aa8727.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7acde.md>)

Recorded evaluation configuration: {"Notes":"Evaluated using authors' scripts"}. This record does not assert independent reproduction.

### Omni-R1

Score: 43. Result ID: 69c2862247f34ce924aa872f.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7acde.md>)

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

### Baichuan-Omni-1.5

Score: 42.9. Result ID: 69c2862247f34ce924aa8726.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bc1e209131cea6ed2e.md>)

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

### Qwen2.5-Omni-7B

Score: 42.1. Result ID: 69c2862247f34ce924aa872c.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

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

### HumanOmniV2

Score: 41.9. Result ID: 69c2862247f34ce924aa8728.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a41e209131cea7ea02.md>)

Recorded evaluation configuration: {"Notes":"Evaluated using authors' scripts"}. This record does not assert independent reproduction.

### ThinkOmni

Score: 39.9. Result ID: 69c2862247f34ce924aa872a.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Omni-3B","LRM Guide":"DeepSeek"}. This record does not assert independent reproduction.

### ThinkOmni

Score: 39.5. Result ID: 69c2862247f34ce924aa872b.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Omni-3B","LRM Guide":"Qwen3"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-3B

Score: 37.5. Result ID: 69c2862247f34ce924aa8729.

[Reporting paper](<https://www.sota2.com/research/paper/69a1251c2d603e6de3e3c643.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.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.
