# Single-Hop Question Answering on Trivia

Source: [Single-Hop Question Answering on Trivia](<https://www.sota2.com/research/sota/single-hop-question-answering-on-trivia>)

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

Data updated: 2026-03-19T08:48:53.037Z

Evaluation of model performance on the Trivia dataset specifically for single-hop question answering tasks, reporting Exact Match (EM) scores.

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 | Single-Hop Question Answering |
| Dataset (including any stated split) | Trivia |
| Metric | Exact Match |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 30 of 30 |
| 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

- [Exact Match](<https://www.sota2.com/research/sota/single-hop-question-answering-on-trivia.md?metric=Exact%20Match>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Exact Match | Result date | Report paper |
| --- | --- | --- | --- |
| Tree-GRPO | 68.1 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 67.4 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 67.2 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 64.5 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 64.2 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 63.5 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 63.3 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 61.5 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 59.9 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 59.7 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 58.8 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 58.2 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 58 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 57.8 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 57.3 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 56.3 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 53.1 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 51 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 48.9 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 48.4 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 47.2 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 44.3 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 43.5 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 42.4 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 40.8 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 30.9 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 29.6 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 28.8 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 22.4 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 22.1 | Not recorded | 68fa7c101e209131cea8c349 |

### Tree-GRPO

Exact Match: 68.1. Result ID: 69bbb87247f34ce924a5a78d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14b"}. This record does not assert independent reproduction.

### GSPO

Exact Match: 67.4. Result ID: 69bbb87247f34ce924a5a78c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea8231d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14b"}. This record does not assert independent reproduction.

### GRPO

Exact Match: 67.2. Result ID: 69bbb87247f34ce924a5a78b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14b"}. This record does not assert independent reproduction.

### GSPO

Exact Match: 64.5. Result ID: 69bbb87247f34ce924a5a786.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea8231d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7b"}. This record does not assert independent reproduction.

### ReAct

Exact Match: 64.2. Result ID: 69bbb87247f34ce924a5a78a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14b"}. This record does not assert independent reproduction.

### Search-o1

Exact Match: 63.5. Result ID: 69bbb87247f34ce924a5a789.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76911e209131cea6dca9.md>)

[Implementation](<https://github.com/sunnynexus/Search-o1>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14b"}. This record does not assert independent reproduction.

### Tree-GRPO

Exact Match: 63.3. Result ID: 69bbb87247f34ce924a5a787.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7b"}. This record does not assert independent reproduction.

### GRPO

Exact Match: 61.5. Result ID: 69bbb87247f34ce924a5a785.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7b"}. This record does not assert independent reproduction.

### Tree-GRPO

Exact Match: 59.9. Result ID: 69bbb87247f34ce924a5a781.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Llama3.2-3b"}. This record does not assert independent reproduction.

### Tree-GRPO

Exact Match: 59.7. Result ID: 69bbb87247f34ce924a5a77b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3b"}. This record does not assert independent reproduction.

### GSPO

Exact Match: 58.8. Result ID: 69bbb87247f34ce924a5a77a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea8231d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3b"}. This record does not assert independent reproduction.

### GRPO

Exact Match: 58.2. Result ID: 69bbb87247f34ce924a5a77f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Backbone":"Llama3.2-3b"}. This record does not assert independent reproduction.

### GRPO

Exact Match: 58. Result ID: 69bbb87247f34ce924a5a779.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3b"}. This record does not assert independent reproduction.

### GSPO

Exact Match: 57.8. Result ID: 69bbb87247f34ce924a5a780.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea8231d.md>)

Recorded evaluation configuration: {"Backbone":"Llama3.2-3b"}. This record does not assert independent reproduction.

### Tree-GRPO

Exact Match: 57.3. Result ID: 69bbb87247f34ce924a5a775.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-1.5b"}. This record does not assert independent reproduction.

### ReAct

Exact Match: 56.3. Result ID: 69bbb87247f34ce924a5a784.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7b"}. This record does not assert independent reproduction.

### Direct Inference

Exact Match: 53.1. Result ID: 69bbb87247f34ce924a5a788.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-14b"}. This record does not assert independent reproduction.

### GRPO

Exact Match: 51. Result ID: 69bbb87247f34ce924a5a773.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-1.5b"}. This record does not assert independent reproduction.

### GSPO

Exact Match: 48.9. Result ID: 69bbb87247f34ce924a5a774.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea8231d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-1.5b"}. This record does not assert independent reproduction.

### Search-o1

Exact Match: 48.4. Result ID: 69bbb87247f34ce924a5a77d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76911e209131cea6dca9.md>)

[Implementation](<https://github.com/sunnynexus/Search-o1>)

Recorded evaluation configuration: {"Backbone":"Llama3.2-3b"}. This record does not assert independent reproduction.

### Search-o1

Exact Match: 47.2. Result ID: 69bbb87247f34ce924a5a783.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76911e209131cea6dca9.md>)

[Implementation](<https://github.com/sunnynexus/Search-o1>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7b"}. This record does not assert independent reproduction.

### Search-o1

Exact Match: 44.3. Result ID: 69bbb87247f34ce924a5a777.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76911e209131cea6dca9.md>)

[Implementation](<https://github.com/sunnynexus/Search-o1>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3b"}. This record does not assert independent reproduction.

### ReAct

Exact Match: 43.5. Result ID: 69bbb87247f34ce924a5a778.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3b"}. This record does not assert independent reproduction.

### ReAct

Exact Match: 42.4. Result ID: 69bbb87247f34ce924a5a77e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

Recorded evaluation configuration: {"Backbone":"Llama3.2-3b"}. This record does not assert independent reproduction.

### Direct Inference

Exact Match: 40.8. Result ID: 69bbb87247f34ce924a5a782.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7b"}. This record does not assert independent reproduction.

### Search-o1

Exact Match: 30.9. Result ID: 69bbb87247f34ce924a5a771.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76911e209131cea6dca9.md>)

[Implementation](<https://github.com/sunnynexus/Search-o1>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-1.5b"}. This record does not assert independent reproduction.

### Direct Inference

Exact Match: 29.6. Result ID: 69bbb87247f34ce924a5a77c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Llama3.2-3b"}. This record does not assert independent reproduction.

### Direct Inference

Exact Match: 28.8. Result ID: 69bbb87247f34ce924a5a776.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-3b"}. This record does not assert independent reproduction.

### Direct Inference

Exact Match: 22.4. Result ID: 69bbb87247f34ce924a5a770.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-1.5b"}. This record does not assert independent reproduction.

### ReAct

Exact Match: 22.1. Result ID: 69bbb87247f34ce924a5a772.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c101e209131cea8c349.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-1.5b"}. This record does not assert independent reproduction.

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