# Multi-Hop Question Answering on Bamb

Source: [Multi-Hop Question Answering on Bamb](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamb>)

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

Data updated: 2026-03-19T08:48:53.069Z

Evaluation of model performance on the Bamb dataset for Multi-Hop Question Answering, reporting the Exact Match (EM) metric.

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 | Multi-Hop Question Answering |
| Dataset (including any stated split) | Bamb |
| Metric | Exact Match (EM) |
| 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 (EM)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamb.md?metric=Exact%20Match%20(EM)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Exact Match (EM) | Result date | Report paper |
| --- | --- | --- | --- |
| Tree-GRPO | 54.4 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 53.6 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 52.8 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 46.4 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 44 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 44 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 43.2 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 43.2 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 43.2 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 41.6 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 36.8 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 36.8 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 32 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 32 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 32 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 32 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 29.6 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 28.8 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 23.2 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 20 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 16 | Not recorded | 68fa7c101e209131cea8c349 |
| Tree-GRPO | 13.6 | Not recorded | 68fa7c101e209131cea8c349 |
| Search-o1 | 13 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 12 | Not recorded | 68fa7c101e209131cea8c349 |
| ReAct | 11.2 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 8 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 8 | Not recorded | 68fa7c101e209131cea8c349 |
| GSPO | 4.8 | Not recorded | 68fa7c101e209131cea8c349 |
| GRPO | 4 | Not recorded | 68fa7c101e209131cea8c349 |
| Direct Inference | 2.4 | Not recorded | 68fa7c101e209131cea8c349 |

### Tree-GRPO

Exact Match (EM): 54.4. Result ID: 69bbb87247f34ce924a5a841.

[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.

### GRPO

Exact Match (EM): 53.6. Result ID: 69bbb87247f34ce924a5a83f.

[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 (EM): 52.8. Result ID: 69bbb87247f34ce924a5a840.

[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.

### Tree-GRPO

Exact Match (EM): 46.4. Result ID: 69bbb87247f34ce924a5a835.

[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.

### GSPO

Exact Match (EM): 44. Result ID: 69bbb87247f34ce924a5a83a.

[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.

### Tree-GRPO

Exact Match (EM): 44. Result ID: 69bbb87247f34ce924a5a83b.

[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.

### Tree-GRPO

Exact Match (EM): 43.2. Result ID: 69bbb87247f34ce924a5a82f.

[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.

### GRPO

Exact Match (EM): 43.2. Result ID: 69bbb87247f34ce924a5a839.

[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.

### ReAct

Exact Match (EM): 43.2. Result ID: 69bbb87247f34ce924a5a83e.

[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 (EM): 41.6. Result ID: 69bbb87247f34ce924a5a83d.

[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.

### GRPO

Exact Match (EM): 36.8. Result ID: 69bbb87247f34ce924a5a82d.

[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 (EM): 36.8. Result ID: 69bbb87247f34ce924a5a82e.

[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.

### Search-o1

Exact Match (EM): 32. Result ID: 69bbb87247f34ce924a5a831.

[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.

### GRPO

Exact Match (EM): 32. Result ID: 69bbb87247f34ce924a5a833.

[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.

### GSPO

Exact Match (EM): 32. Result ID: 69bbb87247f34ce924a5a834.

[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.

### Search-o1

Exact Match (EM): 32. Result ID: 69bbb87247f34ce924a5a837.

[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 (EM): 29.6. Result ID: 69bbb87247f34ce924a5a82b.

[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 (EM): 28.8. Result ID: 69bbb87247f34ce924a5a838.

[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.

### ReAct

Exact Match (EM): 23.2. Result ID: 69bbb87247f34ce924a5a832.

[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.

### ReAct

Exact Match (EM): 20. Result ID: 69bbb87247f34ce924a5a82c.

[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.

### Direct Inference

Exact Match (EM): 16. Result ID: 69bbb87247f34ce924a5a83c.

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

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

### Tree-GRPO

Exact Match (EM): 13.6. Result ID: 69bbb87247f34ce924a5a829.

[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.

### Search-o1

Exact Match (EM): 13. Result ID: 69bbb87247f34ce924a5a825.

[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 (EM): 12. Result ID: 69bbb87247f34ce924a5a836.

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

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

### ReAct

Exact Match (EM): 11.2. Result ID: 69bbb87247f34ce924a5a826.

[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.

### Direct Inference

Exact Match (EM): 8. Result ID: 69bbb87247f34ce924a5a824.

[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.

### Direct Inference

Exact Match (EM): 8. Result ID: 69bbb87247f34ce924a5a830.

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

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

### GSPO

Exact Match (EM): 4.8. Result ID: 69bbb87247f34ce924a5a828.

[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.

### GRPO

Exact Match (EM): 4. Result ID: 69bbb87247f34ce924a5a827.

[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.

### Direct Inference

Exact Match (EM): 2.4. Result ID: 69bbb87247f34ce924a5a82a.

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

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

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