# Forecasting on OracleProto 80 forecasting questions 1.0 (test)

Source: [Forecasting on OracleProto 80 forecasting questions 1.0 (test)](<https://www.sota2.com/research/sota/forecasting-on-oracleproto-80-forecasting-questions-1-0-test>)

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

Data updated: 2026-05-06T08:35:33.335Z

Evaluation of forecasting models on the test split of the OracleProto 80 forecasting questions 1.0 dataset, assessed using pass@n metrics and agreement measures like Cohen’s Kappa.

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 | Forecasting |
| Dataset (including any stated split) | OracleProto 80 forecasting questions 1.0 (test) |
| Metric | Pass@1 Average |
| 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

- [Pass@1 Average](<https://www.sota2.com/research/sota/forecasting-on-oracleproto-80-forecasting-questions-1-0-test.md?metric=Pass%401%20Average>): Higher is better; unit: PERCENT.

- [Pass Any@N](<https://www.sota2.com/research/sota/forecasting-on-oracleproto-80-forecasting-questions-1-0-test.md?metric=Pass%20Any%40N>): Higher is better; unit: PERCENT.

- [Pass All@N](<https://www.sota2.com/research/sota/forecasting-on-oracleproto-80-forecasting-questions-1-0-test.md?metric=Pass%20All%40N>): Higher is better; unit: PERCENT.

- [Cohen’s Kappa (κ)](<https://www.sota2.com/research/sota/forecasting-on-oracleproto-80-forecasting-questions-1-0-test.md?metric=Cohen%E2%80%99s%20Kappa%20(%CE%BA)>): Higher is better; unit: SCALAR.

- [Fleiss’ Kappa (κ)](<https://www.sota2.com/research/sota/forecasting-on-oracleproto-80-forecasting-questions-1-0-test.md?metric=Fleiss%E2%80%99%20Kappa%20(%CE%BA)>): Higher is better; unit: SCALAR.

- [FSS](<https://www.sota2.com/research/sota/forecasting-on-oracleproto-80-forecasting-questions-1-0-test.md?metric=FSS>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 Average | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-V3.2-Exp | 57.56 | Not recorded | 69facb14c0f56ed84308a3da |
| GLM 5 | 56.96 | Not recorded | 69facb14c0f56ed84308a3da |
| Kimi K2.5 | 56.12 | Not recorded | 69facb14c0f56ed84308a3da |
| Qwen3.5-Flash | 55.65 | Not recorded | 69facb14c0f56ed84308a3da |
| MiniMax M2.5 | 53.14 | Not recorded | 69facb14c0f56ed84308a3da |
| Doubao Seed 2.0 Lite | 50.56 | Not recorded | 69facb14c0f56ed84308a3da |

### DeepSeek-V3.2-Exp

Pass@1 Average: 57.56. Result ID: 69fafc5b47f34ce924dde756.

[Reporting paper](<https://www.sota2.com/research/paper/69facb14c0f56ed84308a3da.md>)

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

### GLM 5

Pass@1 Average: 56.96. Result ID: 69fafc5b47f34ce924dde757.

[Reporting paper](<https://www.sota2.com/research/paper/69facb14c0f56ed84308a3da.md>)

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

### Kimi K2.5

Pass@1 Average: 56.12. Result ID: 69fafc5b47f34ce924dde75a.

[Reporting paper](<https://www.sota2.com/research/paper/69facb14c0f56ed84308a3da.md>)

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

### Qwen3.5-Flash

Pass@1 Average: 55.65. Result ID: 69fafc5b47f34ce924dde758.

[Reporting paper](<https://www.sota2.com/research/paper/69facb14c0f56ed84308a3da.md>)

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

### MiniMax M2.5

Pass@1 Average: 53.14. Result ID: 69fafc5b47f34ce924dde759.

[Reporting paper](<https://www.sota2.com/research/paper/69facb14c0f56ed84308a3da.md>)

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

### Doubao Seed 2.0 Lite

Pass@1 Average: 50.56. Result ID: 69fafc5b47f34ce924dde75b.

[Reporting paper](<https://www.sota2.com/research/paper/69facb14c0f56ed84308a3da.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.