# Event-Event Temporal Reasoning (L3) on TEMPREASON 1.0 (test)

Source: [Event-Event Temporal Reasoning (L3) on TEMPREASON 1.0 (test)](<https://www.sota2.com/research/sota/event-event-temporal-reasoning-l3-on-tempreason-1-0-test>)

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

Data updated: 2026-02-26T05:41:34.802Z

Evaluation of model performance on the test split of the TEMPREASON 1.0 dataset for Event-Event Temporal Reasoning capabilities at Level 3, measured using EM, F1, and Delta F1.

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 | Event-Event Temporal Reasoning (L3) |
| Dataset (including any stated split) | TEMPREASON 1.0 (test) |
| Metric | EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [EM](<https://www.sota2.com/research/sota/event-event-temporal-reasoning-l3-on-tempreason-1-0-test.md?metric=EM>): Higher is better; unit: PERCENT.

- [F1](<https://www.sota2.com/research/sota/event-event-temporal-reasoning-l3-on-tempreason-1-0-test.md?metric=F1>): Higher is better; unit: PERCENT.

- [Delta F1](<https://www.sota2.com/research/sota/event-event-temporal-reasoning-l3-on-tempreason-1-0-test.md?metric=Delta%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| TempT5 | 8110 | Not recorded | 68fa6fde1e209131cea47c3f |
| T5-SFT | 7820 | Not recorded | 68fa6fde1e209131cea47c3f |
| ChatGPT | 4950 | Not recorded | 68fa6fde1e209131cea47c3f |
| FLAN-T5-L | 3630 | Not recorded | 68fa6fde1e209131cea47c3f |
| TempT5 | 2110 | Not recorded | 68fa6fde1e209131cea47c3f |
| T5-SFT | 1970 | Not recorded | 68fa6fde1e209131cea47c3f |
| ChatGPT | 1700 | Not recorded | 68fa6fde1e209131cea47c3f |
| TempT5 | 1230 | Not recorded | 68fa6fde1e209131cea47c3f |
| T5-SFT | 1210 | Not recorded | 68fa6fde1e209131cea47c3f |
| ChatGPT | 1200 | Not recorded | 68fa6fde1e209131cea47c3f |
| FLAN-T5-L | 810 | Not recorded | 68fa6fde1e209131cea47c3f |
| FLAN-T5-L | 40 | Not recorded | 68fa6fde1e209131cea47c3f |

### TempT5

EM: 8110. Result ID: 6990efc03a6c314849046cec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/TempReason>)

Recorded evaluation configuration: {"Setting":"ReasonQA"}. This record does not assert independent reproduction.

### T5-SFT

EM: 7820. Result ID: 6990efc03a6c314849046ce9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Setting":"ReasonQA"}. This record does not assert independent reproduction.

### ChatGPT

EM: 4950. Result ID: 6990efc03a6c314849046ce6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

Recorded evaluation configuration: {"Setting":"ReasonQA"}. This record does not assert independent reproduction.

### FLAN-T5-L

EM: 3630. Result ID: 6990efc03a6c314849046ce3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bc51e209131cea30383.md>)

[Implementation](<https://github.com/google-research/flan>)

Recorded evaluation configuration: {"Setting":"ReasonQA"}. This record does not assert independent reproduction.

### TempT5

EM: 2110. Result ID: 6990efc03a6c314849046ced.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/TempReason>)

Recorded evaluation configuration: {"Setting":"OBQA"}. This record does not assert independent reproduction.

### T5-SFT

EM: 1970. Result ID: 6990efc03a6c314849046cea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Setting":"OBQA"}. This record does not assert independent reproduction.

### ChatGPT

EM: 1700. Result ID: 6990efc03a6c314849046ce7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

Recorded evaluation configuration: {"Setting":"OBQA"}. This record does not assert independent reproduction.

### TempT5

EM: 1230. Result ID: 6990efc03a6c314849046ceb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/TempReason>)

Recorded evaluation configuration: {"Setting":"CBQA"}. This record does not assert independent reproduction.

### T5-SFT

EM: 1210. Result ID: 6990efc03a6c314849046ce8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Setting":"CBQA"}. This record does not assert independent reproduction.

### ChatGPT

EM: 1200. Result ID: 6990efc03a6c314849046ce5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

Recorded evaluation configuration: {"Setting":"CBQA"}. This record does not assert independent reproduction.

### FLAN-T5-L

EM: 810. Result ID: 6990efc03a6c314849046ce4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bc51e209131cea30383.md>)

[Implementation](<https://github.com/google-research/flan>)

Recorded evaluation configuration: {"Setting":"OBQA"}. This record does not assert independent reproduction.

### FLAN-T5-L

EM: 40. Result ID: 6990efc03a6c314849046ce2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bc51e209131cea30383.md>)

[Implementation](<https://github.com/google-research/flan>)

Recorded evaluation configuration: {"Setting":"CBQA"}. This record does not assert independent reproduction.

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