# Climate Discovery on ClimaBench 2025

Source: [Climate Discovery on ClimaBench 2025](<https://www.sota2.com/research/sota/climate-discovery-on-climabench-2025>)

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

Data updated: 2026-04-21T09:15:49.735Z

Evaluation of model performance on the ClimaBench 2025 dataset for Climate Discovery tasks, reporting metrics such as AE, SC, PS, RBA, and Overall score.

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 | Climate Discovery |
| Dataset (including any stated split) | ClimaBench 2025 |
| Metric | AE Score |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 18 of 18 |
| 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 Score](<https://www.sota2.com/research/sota/climate-discovery-on-climabench-2025.md?metric=AE%20Score>): Lower is better; unit: SCALAR.

- [SC Score](<https://www.sota2.com/research/sota/climate-discovery-on-climabench-2025.md?metric=SC%20Score>): Higher is better; unit: SCALAR.

- [PS Score](<https://www.sota2.com/research/sota/climate-discovery-on-climabench-2025.md?metric=PS%20Score>): Higher is better; unit: SCALAR.

- [RBA Score](<https://www.sota2.com/research/sota/climate-discovery-on-climabench-2025.md?metric=RBA%20Score>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/climate-discovery-on-climabench-2025.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AE Score | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-R1 | 7.55 | Not recorded | 69e704bb7d0172140ec7ee73 |
| Qwen3-235B | 7.58 | Not recorded | 69e704bb7d0172140ec7ee73 |
| GPT-4o | 7.72 | Not recorded | 69e704bb7d0172140ec7ee73 |
| ResearchAgent | 8.12 | Not recorded | 69e704bb7d0172140ec7ee73 |
| DS-Agent | 8.12 | Not recorded | 69e704bb7d0172140ec7ee73 |
| ResearchAgent | 8.15 | Not recorded | 69e704bb7d0172140ec7ee73 |
| DS-Agent | 8.15 | Not recorded | 69e704bb7d0172140ec7ee73 |
| ResearchAgent | 8.18 | Not recorded | 69e704bb7d0172140ec7ee73 |
| DS-Agent | 8.31 | Not recorded | 69e704bb7d0172140ec7ee73 |
| DeepAnalyze | 8.58 | Not recorded | 69e704bb7d0172140ec7ee73 |
| DeepAnalyze | 8.58 | Not recorded | 69e704bb7d0172140ec7ee73 |
| DeepAnalyze | 8.58 | Not recorded | 69e704bb7d0172140ec7ee73 |
| Agent Laboratory | 8.82 | Not recorded | 69e704bb7d0172140ec7ee73 |
| ClimAgent | 8.95 | Not recorded | 69e704bb7d0172140ec7ee73 |
| Agent Laboratory | 8.95 | Not recorded | 69e704bb7d0172140ec7ee73 |
| Agent Laboratory | 8.98 | Not recorded | 69e704bb7d0172140ec7ee73 |
| ClimAgent | 9.58 | Not recorded | 69e704bb7d0172140ec7ee73 |
| ClimAgent | 9.62 | Not recorded | 69e704bb7d0172140ec7ee73 |

### DeepSeek-R1

AE Score: 7.55. Result ID: 69e7403b47f34ce924cdbba6.

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

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### Qwen3-235B

AE Score: 7.58. Result ID: 69e7403b47f34ce924cdbbac.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cdc5.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-235B"}. This record does not assert independent reproduction.

### GPT-4o

AE Score: 7.72. Result ID: 69e7403b47f34ce924cdbba0.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### ResearchAgent

AE Score: 8.12. Result ID: 69e7403b47f34ce924cdbba2.

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

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### DS-Agent

AE Score: 8.12. Result ID: 69e7403b47f34ce924cdbba7.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73601e209131cea5c01c.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### ResearchAgent

AE Score: 8.15. Result ID: 69e7403b47f34ce924cdbba8.

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

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### DS-Agent

AE Score: 8.15. Result ID: 69e7403b47f34ce924cdbbad.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73601e209131cea5c01c.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-235B"}. This record does not assert independent reproduction.

### ResearchAgent

AE Score: 8.18. Result ID: 69e7403b47f34ce924cdbbae.

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

Recorded evaluation configuration: {"Backbone":"Qwen3-235B"}. This record does not assert independent reproduction.

### DS-Agent

AE Score: 8.31. Result ID: 69e7403b47f34ce924cdbba1.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73601e209131cea5c01c.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### DeepAnalyze

AE Score: 8.58. Result ID: 69e7403b47f34ce924cdbba4.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c561e209131cea8da41.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### DeepAnalyze

AE Score: 8.58. Result ID: 69e7403b47f34ce924cdbbaa.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c561e209131cea8da41.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### DeepAnalyze

AE Score: 8.58. Result ID: 69e7403b47f34ce924cdbbb0.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c561e209131cea8da41.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-235B"}. This record does not assert independent reproduction.

### Agent Laboratory

AE Score: 8.82. Result ID: 69e7403b47f34ce924cdbba3.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfc9.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### ClimAgent

AE Score: 8.95. Result ID: 69e7403b47f34ce924cdbba5.

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

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

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### Agent Laboratory

AE Score: 8.95. Result ID: 69e7403b47f34ce924cdbba9.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfc9.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### Agent Laboratory

AE Score: 8.98. Result ID: 69e7403b47f34ce924cdbbaf.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfc9.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-235B"}. This record does not assert independent reproduction.

### ClimAgent

AE Score: 9.58. Result ID: 69e7403b47f34ce924cdbbab.

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

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

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### ClimAgent

AE Score: 9.62. Result ID: 69e7403b47f34ce924cdbbb1.

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

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

Recorded evaluation configuration: {"Backbone":"Qwen3-235B"}. This record does not assert independent reproduction.

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