# Open-ended Climate Analysis on ClimaBench 100-sample Human-Evaluated Subset

Source: [Open-ended Climate Analysis on ClimaBench 100-sample Human-Evaluated Subset](<https://www.sota2.com/research/sota/open-ended-climate-analysis-on-climabench-100-sample-human-evaluated-subset>)

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

Data updated: 2026-04-21T09:15:49.663Z

Evaluation of model performance on the 100-sample human-evaluated subset of ClimaBench for open-ended climate analysis tasks, reporting metrics such as AE, SC, PS, and RBA.

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 | Open-ended Climate Analysis |
| Dataset (including any stated split) | ClimaBench 100-sample Human-Evaluated Subset |
| Metric | AE |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [AE](<https://www.sota2.com/research/sota/open-ended-climate-analysis-on-climabench-100-sample-human-evaluated-subset.md?metric=AE>): Higher is better; unit: SCALAR.

- [SC](<https://www.sota2.com/research/sota/open-ended-climate-analysis-on-climabench-100-sample-human-evaluated-subset.md?metric=SC>): Higher is better; unit: SCALAR.

- [PS](<https://www.sota2.com/research/sota/open-ended-climate-analysis-on-climabench-100-sample-human-evaluated-subset.md?metric=PS>): Higher is better; unit: SCALAR.

- [RBA](<https://www.sota2.com/research/sota/open-ended-climate-analysis-on-climabench-100-sample-human-evaluated-subset.md?metric=RBA>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/open-ended-climate-analysis-on-climabench-100-sample-human-evaluated-subset.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AE | Result date | Report paper |
| --- | --- | --- | --- |
| Human Team | 9.42 | Not recorded | 69e704bb7d0172140ec7ee73 |
| ClimAgent | 9.34 | Not recorded | 69e704bb7d0172140ec7ee73 |

### Human Team

AE: 9.42. Result ID: 69e7403b47f34ce924cdbb8c.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee73.md>)

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

### ClimAgent

AE: 9.34. Result ID: 69e7403b47f34ce924cdbb8d.

[Reporting paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704bb7d0172140ec7ee73.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.