# Multitask Language Understanding on MILU

Source: [Multitask Language Understanding on MILU](<https://www.sota2.com/research/sota/multitask-language-understanding-on-milu>)

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

Data updated: 2026-03-05T07:37:30.697Z

Evaluation of model performance on the MILU benchmark for Multitask Language Understanding, reporting Accuracy.

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 | Multitask Language Understanding |
| Dataset (including any stated split) | MILU |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/multitask-language-understanding-on-milu.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-1.7B | 37 | Not recorded | 69a90de82d603e6de3e4065d |
| gemma-2-2b-it | 36 | Not recorded | 69a90de82d603e6de3e4065d |
| gemma-2-2b | 33 | Not recorded | 69a90de82d603e6de3e4065d |
| OpenHathi-7B-Hi-v0.1-Base | 30 | Not recorded | 69a90de82d603e6de3e4065d |
| Qwen3-0.6B-Base | 30 | Not recorded | 69a90de82d603e6de3e4065d |
| Qwen2.5-1.5B | 30 | Not recorded | 69a90de82d603e6de3e4065d |
| Qwen-2.5-1.5B-Instruct | 30 | Not recorded | 69a90de82d603e6de3e4065d |
| gemma-3-1b-it | 29 | Not recorded | 69a90de82d603e6de3e4065d |
| LilMoo-v0.2 | 28 | Not recorded | 69a90de82d603e6de3e4065d |
| LilMoo-v0.1 | 28 | Not recorded | 69a90de82d603e6de3e4065d |
| Airavata | 28 | Not recorded | 69a90de82d603e6de3e4065d |
| Llama-3.2-1B-Instruct | 28 | Not recorded | 69a90de82d603e6de3e4065d |
| Llama-3.2-1B | 27 | Not recorded | 69a90de82d603e6de3e4065d |
| gemma-3-1b-pt | 25 | Not recorded | 69a90de82d603e6de3e4065d |

### Qwen3-1.7B

Accuracy: 37. Result ID: 69a931ab6dbb7075b9523d05.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### gemma-2-2b-it

Accuracy: 36. Result ID: 69a931ab6dbb7075b9523d08.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea5973c.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### gemma-2-2b

Accuracy: 33. Result ID: 69a931ac6dbb7075b9523d0d.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea5973c.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### OpenHathi-7B-Hi-v0.1-Base

Accuracy: 30. Result ID: 69a931ab6dbb7075b9523d06.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### Qwen3-0.6B-Base

Accuracy: 30. Result ID: 69a931ac6dbb7075b9523d0b.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### Qwen2.5-1.5B

Accuracy: 30. Result ID: 69a931ac6dbb7075b9523d0e.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b71e209131cea6981e.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### Qwen-2.5-1.5B-Instruct

Accuracy: 30. Result ID: 69a931ac6dbb7075b9523d10.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b71e209131cea6981e.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### gemma-3-1b-it

Accuracy: 29. Result ID: 69a931ac6dbb7075b9523d09.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### LilMoo-v0.2

Accuracy: 28. Result ID: 69a931ab6dbb7075b9523d03.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### LilMoo-v0.1

Accuracy: 28. Result ID: 69a931ab6dbb7075b9523d04.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### Airavata

Accuracy: 28. Result ID: 69a931ab6dbb7075b9523d07.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### Llama-3.2-1B-Instruct

Accuracy: 28. Result ID: 69a931ac6dbb7075b9523d0c.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### Llama-3.2-1B

Accuracy: 27. Result ID: 69a931ac6dbb7075b9523d0f.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### gemma-3-1b-pt

Accuracy: 25. Result ID: 69a931ac6dbb7075b9523d0a.

[Reporting paper](<https://www.sota2.com/research/paper/69a90de82d603e6de3e4065d.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

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