# LLM Tutoring Evaluation on TutorBench

Source: [LLM Tutoring Evaluation on TutorBench](<https://www.sota2.com/research/sota/llm-tutoring-evaluation-on-tutorbench>)

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

Data updated: 2026-04-09T23:18:13.591Z

Evaluation of LLM performance in a tutoring context using the TutorBench dataset, reporting scores across Text-Only, Multimodal, and Overall dimensions.

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 | LLM Tutoring Evaluation |
| Dataset (including any stated split) | TutorBench |
| Metric | Text-Only Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Text-Only Score](<https://www.sota2.com/research/sota/llm-tutoring-evaluation-on-tutorbench.md?metric=Text-Only%20Score>): Higher is better; unit: PERCENT.

- [Multimodal Score](<https://www.sota2.com/research/sota/llm-tutoring-evaluation-on-tutorbench.md?metric=Multimodal%20Score>): Higher is better; unit: PERCENT.

- [Overall Score](<https://www.sota2.com/research/sota/llm-tutoring-evaluation-on-tutorbench.md?metric=Overall%20Score>): Higher is better; unit: PERCENT.

- [Tutor Bench Score](<https://www.sota2.com/research/sota/llm-tutoring-evaluation-on-tutorbench.md?metric=Tutor%20Bench%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Text-Only Score | Result date | Report paper |
| --- | --- | --- | --- |
| EDUQWEN 30B-VL-SFT | 64.1 | Not recorded | 69d732717d0172140ec76a15 |
| QWEN3-30B-VL (BASE MODEL) | 60.21 | Not recorded | 69d732717d0172140ec76a15 |
| GEMINI-3PRO | 58.41 | Not recorded | 69d732717d0172140ec76a15 |

### EDUQWEN 30B-VL-SFT

Text-Only Score: 64.1. Result ID: 69d833a647f34ce924bfe1a1.

[Reporting paper](<https://www.sota2.com/research/paper/69d732717d0172140ec76a15.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d732717d0172140ec76a15.md>)

Recorded evaluation configuration: {"Judge Model":"CLAUDE-4.5-SONNET"}. This record does not assert independent reproduction.

### QWEN3-30B-VL (BASE MODEL)

Text-Only Score: 60.21. Result ID: 69d833a647f34ce924bfe1a0.

[Reporting paper](<https://www.sota2.com/research/paper/69d732717d0172140ec76a15.md>)

Recorded evaluation configuration: {"Judge Model":"CLAUDE-4.5-SONNET"}. This record does not assert independent reproduction.

### GEMINI-3PRO

Text-Only Score: 58.41. Result ID: 69d833a647f34ce924bfe19f.

[Reporting paper](<https://www.sota2.com/research/paper/69d732717d0172140ec76a15.md>)

Recorded evaluation configuration: {"Judge Model":"CLAUDE-4.5-SONNET"}. This record does not assert independent reproduction.

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