# Pairwise evaluator agreement with human judgment on Procthor-10K Complex 1.0 (test)

Source: [Pairwise evaluator agreement with human judgment on Procthor-10K Complex 1.0 (test)](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test>)

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

Data updated: 2026-04-15T10:22:56.349Z

Evaluation of model performance using pairwise comparison against human judgments on the Procthor-10K Complex 1.0 test set. Agreement is measured across Semantic, Orientation, and Overlap criteria using metrics like IAA, Fleiss' Kappa, and specific evaluator scores (SceneCritic, VLM).

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 | Pairwise evaluator agreement with human judgment |
| Dataset (including any stated split) | Procthor-10K Complex 1.0 (test) |
| Metric | Method A SceneCritic Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Method A SceneCritic Score](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Method%20A%20SceneCritic%20Score>): Higher is better; unit: PERCENT.

- [Method A VLM Score](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Method%20A%20VLM%20Score>): Higher is better; unit: PERCENT.

- [Method B SceneCritic Score](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Method%20B%20SceneCritic%20Score>): Higher is better; unit: PERCENT.

- [Method B VLM Score](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Method%20B%20VLM%20Score>): Higher is better; unit: PERCENT.

- [Semantic Win Rate A](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Semantic%20Win%20Rate%20A>): Higher is better; unit: PERCENT.

- [Semantic Win Rate B](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Semantic%20Win%20Rate%20B>): Higher is better; unit: PERCENT.

- [Orientation Win Rate A](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Orientation%20Win%20Rate%20A>): Higher is better; unit: PERCENT.

- [Orientation Win Rate B](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Orientation%20Win%20Rate%20B>): Higher is better; unit: PERCENT.

- [Overlap Win Rate A](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Overlap%20Win%20Rate%20A>): Higher is better; unit: PERCENT.

- [Overlap Win Rate B](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Overlap%20Win%20Rate%20B>): Higher is better; unit: PERCENT.

- [IAA Semantic](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=IAA%20Semantic>): Higher is better; unit: PERCENT.

- [IAA Orientation](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=IAA%20Orientation>): Higher is better; unit: PERCENT.

- [IAA Overlap](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=IAA%20Overlap>): Higher is better; unit: PERCENT.

- [Fleiss' Kappa Semantic](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Fleiss%27%20Kappa%20Semantic>): Higher is better; unit: SCALAR.

- [Fleiss' Kappa Orientation](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Fleiss%27%20Kappa%20Orientation>): Higher is better; unit: SCALAR.

- [Fleiss' Kappa Overlap](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=Fleiss%27%20Kappa%20Overlap>): Higher is better; unit: SCALAR.

- [VLM Agreement Semantic](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=VLM%20Agreement%20Semantic>): Higher is better; unit: PERCENT.

- [VLM Agreement Orientation](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=VLM%20Agreement%20Orientation>): Higher is better; unit: PERCENT.

- [VLM Agreement Overlap](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=VLM%20Agreement%20Overlap>): Higher is better; unit: PERCENT.

- [SceneCritic Agreement Semantic](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=SceneCritic%20Agreement%20Semantic>): Higher is better; unit: PERCENT.

- [SceneCritic Agreement Orientation](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=SceneCritic%20Agreement%20Orientation>): Higher is better; unit: PERCENT.

- [SceneCritic Agreement Overlap](<https://www.sota2.com/research/sota/pairwise-evaluator-agreement-with-human-judgment-on-procthor-10k-complex-1-0-test.md?metric=SceneCritic%20Agreement%20Overlap>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Method A SceneCritic Score | Result date | Report paper |
| --- | --- | --- | --- |
| SceneCritic | 79.5 | Not recorded | 69df1bcb7d0172140ec7bc2c |
| SceneCritic | 79.5 | Not recorded | 69df1bcb7d0172140ec7bc2c |
| SceneCritic | 79.39 | Not recorded | 69df1bcb7d0172140ec7bc2c |
| SceneCritic | 79.39 | Not recorded | 69df1bcb7d0172140ec7bc2c |
| SceneCritic | 79.39 | Not recorded | 69df1bcb7d0172140ec7bc2c |
| SceneCritic | 68.3 | Not recorded | 69df1bcb7d0172140ec7bc2c |

### SceneCritic

Method A SceneCritic Score: 79.5. Result ID: 69df667247f34ce924c8bebb.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

Recorded evaluation configuration: {"Method A":"holodeck","Method B":"layoutgpt","Difficulty":"Complex"}. This record does not assert independent reproduction.

### SceneCritic

Method A SceneCritic Score: 79.5. Result ID: 69df667247f34ce924c8bebc.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

Recorded evaluation configuration: {"Method A":"holodeck","Method B":"layoutvlm","Difficulty":"Complex"}. This record does not assert independent reproduction.

### SceneCritic

Method A SceneCritic Score: 79.39. Result ID: 69df667247f34ce924c8beb8.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

Recorded evaluation configuration: {"Method A":"heuristic","Method B":"holodeck","Difficulty":"Complex"}. This record does not assert independent reproduction.

### SceneCritic

Method A SceneCritic Score: 79.39. Result ID: 69df667247f34ce924c8beb9.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

Recorded evaluation configuration: {"Method A":"heuristic","Method B":"layoutgpt","Difficulty":"Complex"}. This record does not assert independent reproduction.

### SceneCritic

Method A SceneCritic Score: 79.39. Result ID: 69df667247f34ce924c8beba.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

Recorded evaluation configuration: {"Method A":"heuristic","Method B":"layoutvlm","Difficulty":"Complex"}. This record does not assert independent reproduction.

### SceneCritic

Method A SceneCritic Score: 68.3. Result ID: 69df667247f34ce924c8bebd.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bcb7d0172140ec7bc2c.md>)

Recorded evaluation configuration: {"Method A":"layoutgpt","Method B":"layoutvlm","Difficulty":"Complex"}. This record does not assert independent reproduction.

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