# Model Ranking Agreement on MT-Bench Arena-derived reference ranking 1.0 (test)

Source: [Model Ranking Agreement on MT-Bench Arena-derived reference ranking 1.0 (test)](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test>)

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

Data updated: 2026-06-17T07:18:19.346Z

Evaluation of model ranking agreement scores across specific skill categories (Coding, Math, STEM, etc.) derived from the MT-Bench Arena reference ranking dataset version 1.0 (test set).

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 | Model Ranking Agreement |
| Dataset (including any stated split) | MT-Bench Arena-derived reference ranking 1.0 (test) |
| Metric | Coding Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Coding Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Coding%20Score>): Higher is better; unit: SCALAR.

- [Extraction Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Extraction%20Score>): Higher is better; unit: SCALAR.

- [Humanities Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Humanities%20Score>): Higher is better; unit: SCALAR.

- [Math Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Math%20Score>): Higher is better; unit: SCALAR.

- [Reasoning Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Reasoning%20Score>): Higher is better; unit: SCALAR.

- [Roleplay Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Roleplay%20Score>): Higher is better; unit: SCALAR.

- [STEM Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=STEM%20Score>): Higher is better; unit: SCALAR.

- [Writing Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Writing%20Score>): Higher is better; unit: SCALAR.

- [Average Agreement Score](<https://www.sota2.com/research/sota/model-ranking-agreement-on-mt-bench-arena-derived-reference-ranking-1-0-test.md?metric=Average%20Agreement%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Coding Score | Result date | Report paper |
| --- | --- | --- | --- |
| Sample25→20 | 121 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| Single→20 | 83 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| Single→20 | 83 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| ScoreWin40 | 79 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| Sample25→20 | 78 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| Random50→20×10 | 76 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| NoTrunc boot | 75 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| BlockTop2 | 73 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| Trunc25→20 | 70 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| Random50→20×10 | 69 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| NoTrunc boot | 66 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| BlockTop1 | 65 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| ScoreWin40 | 60 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| BlockTop1 | 54 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| BlockTop2 | 53 | Not recorded | 6a3229ffd33dfb23e783ea4a |
| Trunc25→20 | 52 | Not recorded | 6a3229ffd33dfb23e783ea4a |

### Sample25→20

Coding Score: 121. Result ID: 6a324a23fbc373592c2f6362.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### Single→20

Coding Score: 83. Result ID: 6a324a23fbc373592c2f6366.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### Single→20

Coding Score: 83. Result ID: 6a324a23fbc373592c2f636e.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

### ScoreWin40

Coding Score: 79. Result ID: 6a324a23fbc373592c2f6364.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### Sample25→20

Coding Score: 78. Result ID: 6a324a23fbc373592c2f636a.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

### Random50→20×10

Coding Score: 76. Result ID: 6a324a23fbc373592c2f6365.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### NoTrunc boot

Coding Score: 75. Result ID: 6a324a23fbc373592c2f6363.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### BlockTop2

Coding Score: 73. Result ID: 6a324a23fbc373592c2f6360.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### Trunc25→20

Coding Score: 70. Result ID: 6a324a23fbc373592c2f635f.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### Random50→20×10

Coding Score: 69. Result ID: 6a324a23fbc373592c2f636d.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

### NoTrunc boot

Coding Score: 66. Result ID: 6a324a23fbc373592c2f636b.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

### BlockTop1

Coding Score: 65. Result ID: 6a324a23fbc373592c2f6361.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"GPT-5"}. This record does not assert independent reproduction.

### ScoreWin40

Coding Score: 60. Result ID: 6a324a23fbc373592c2f636c.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

### BlockTop1

Coding Score: 54. Result ID: 6a324a23fbc373592c2f6369.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

### BlockTop2

Coding Score: 53. Result ID: 6a324a23fbc373592c2f6368.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

### Trunc25→20

Coding Score: 52. Result ID: 6a324a23fbc373592c2f6367.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229ffd33dfb23e783ea4a.md>)

Recorded evaluation configuration: {"Judge":"Prometheus"}. This record does not assert independent reproduction.

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