# Tool-use Question Answering on ToolQA Easy 1.0

Source: [Tool-use Question Answering on ToolQA Easy 1.0](<https://www.sota2.com/research/sota/tool-use-question-answering-on-toolqa-easy-1-0>)

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

Data updated: 2026-02-26T06:09:04.681Z

Evaluation of model performance on the ToolQA Easy 1.0 dataset for Tool-use Question Answering, reporting domain-specific accuracies (Yelp, SciREX, Flight, Airbnb, Coffee).

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 | Tool-use Question Answering |
| Dataset (including any stated split) | ToolQA Easy 1.0 |
| Metric | Yelp Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Yelp Acc](<https://www.sota2.com/research/sota/tool-use-question-answering-on-toolqa-easy-1-0.md?metric=Yelp%20Acc>): Higher is better; unit: PERCENT.

- [SciREX Acc](<https://www.sota2.com/research/sota/tool-use-question-answering-on-toolqa-easy-1-0.md?metric=SciREX%20Acc>): Higher is better; unit: PERCENT.

- [Flight Acc](<https://www.sota2.com/research/sota/tool-use-question-answering-on-toolqa-easy-1-0.md?metric=Flight%20Acc>): Higher is better; unit: PERCENT.

- [Airbnb Acc](<https://www.sota2.com/research/sota/tool-use-question-answering-on-toolqa-easy-1-0.md?metric=Airbnb%20Acc>): Higher is better; unit: PERCENT.

- [Coffee Acc](<https://www.sota2.com/research/sota/tool-use-question-answering-on-toolqa-easy-1-0.md?metric=Coffee%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Yelp Acc | Result date | Report paper |
| --- | --- | --- | --- |
| React | 90 | Not recorded | 69311572d6b0dd3342933a6d |
| Reflexion | 87 | Not recorded | 69311572d6b0dd3342933a6d |
| React | 76 | Not recorded | 69311572d6b0dd3342933a6d |
| React | 71 | Not recorded | 69311572d6b0dd3342933a6d |
| RP-ReAct | 68 | Not recorded | 69311572d6b0dd3342933a6d |
| RP-ReAct | 61 | Not recorded | 69311572d6b0dd3342933a6d |
| RP-ReAct | 53 | Not recorded | 69311572d6b0dd3342933a6d |
| Reflexion | 43 | Not recorded | 69311572d6b0dd3342933a6d |
| Reflexion | 39 | Not recorded | 69311572d6b0dd3342933a6d |
| RP-ReAct | 30 | Not recorded | 69311572d6b0dd3342933a6d |
| RP-ReAct | 26 | Not recorded | 69311572d6b0dd3342933a6d |
| React-100 | 22 | Not recorded | 69311572d6b0dd3342933a6d |
| ReAct | 17 | Not recorded | 69311572d6b0dd3342933a6d |
| React | 15 | Not recorded | 69311572d6b0dd3342933a6d |
| ReAct | 11 | Not recorded | 69311572d6b0dd3342933a6d |
| RP-ReAct | 11 | Not recorded | 69311572d6b0dd3342933a6d |
| Reflexion | 4 | Not recorded | 69311572d6b0dd3342933a6d |

### React

Yelp Acc: 90. Result ID: 699631085698665ec472f3d9.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

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

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

Recorded evaluation configuration: {"Agent Approach":"React","Model":"gpt-oss-120b"}. This record does not assert independent reproduction.

### Reflexion

Yelp Acc: 87. Result ID: 699631085698665ec472f3da.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cc1e209131cea4d38e.md>)

[Implementation](<https://github.com/noahshinn024/reflexion>)

Recorded evaluation configuration: {"Agent Approach":"Reflexion","Model":"gpt-oss-120b"}. This record does not assert independent reproduction.

### React

Yelp Acc: 76. Result ID: 699631085698665ec472f3dc.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

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

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

Recorded evaluation configuration: {"Agent Approach":"React","Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### React

Yelp Acc: 71. Result ID: 699631085698665ec472f3e3.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

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

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

Recorded evaluation configuration: {"Agent Approach":"React","Model":"Qwen3-14B"}. This record does not assert independent reproduction.

### RP-ReAct

Yelp Acc: 68. Result ID: 699631085698665ec472f3de.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

Recorded evaluation configuration: {"Agent Approach":"RP-ReAct","Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### RP-ReAct

Yelp Acc: 61. Result ID: 699631085698665ec472f3e5.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

Recorded evaluation configuration: {"Agent Approach":"RP-ReAct","Model":"Qwen3-14B"}. This record does not assert independent reproduction.

### RP-ReAct

Yelp Acc: 53. Result ID: 699631085698665ec472f3db.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

Recorded evaluation configuration: {"Agent Approach":"RP-ReAct","Model":"gpt-oss-120b"}. This record does not assert independent reproduction.

### Reflexion

Yelp Acc: 43. Result ID: 699631085698665ec472f3e4.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cc1e209131cea4d38e.md>)

[Implementation](<https://github.com/noahshinn024/reflexion>)

Recorded evaluation configuration: {"Agent Approach":"Reflexion","Model":"Qwen3-14B"}. This record does not assert independent reproduction.

### Reflexion

Yelp Acc: 39. Result ID: 699631085698665ec472f3dd.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cc1e209131cea4d38e.md>)

[Implementation](<https://github.com/noahshinn024/reflexion>)

Recorded evaluation configuration: {"Agent Approach":"Reflexion","Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### RP-ReAct

Yelp Acc: 30. Result ID: 699631085698665ec472f3e7.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

Recorded evaluation configuration: {"Agent Approach":"RP-ReAct","Model":"DeepSeek-8B"}. This record does not assert independent reproduction.

### RP-ReAct

Yelp Acc: 26. Result ID: 699631085698665ec472f3e2.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

Recorded evaluation configuration: {"Agent Approach":"RP-ReAct","Model":"gpt-oss-20b"}. This record does not assert independent reproduction.

### React-100

Yelp Acc: 22. Result ID: 699631085698665ec472f3e0.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

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

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

Recorded evaluation configuration: {"Agent Approach":"React-100","Model":"gpt-oss-20b"}. This record does not assert independent reproduction.

### ReAct

Yelp Acc: 17. Result ID: 699631085698665ec472f3e6.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

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

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

Recorded evaluation configuration: {"Agent Approach":"ReAct","Model":"DeepSeek-8B"}. This record does not assert independent reproduction.

### React

Yelp Acc: 15. Result ID: 699631085698665ec472f3df.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

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

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

Recorded evaluation configuration: {"Agent Approach":"React","Model":"gpt-oss-20b"}. This record does not assert independent reproduction.

### ReAct

Yelp Acc: 11. Result ID: 699631085698665ec472f3e8.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

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

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

Recorded evaluation configuration: {"Agent Approach":"ReAct","Model":"DeepSeek-7B"}. This record does not assert independent reproduction.

### RP-ReAct

Yelp Acc: 11. Result ID: 699631085698665ec472f3e9.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

Recorded evaluation configuration: {"Agent Approach":"RP-ReAct","Model":"DeepSeek-7B"}. This record does not assert independent reproduction.

### Reflexion

Yelp Acc: 4. Result ID: 699631085698665ec472f3e1.

[Reporting paper](<https://www.sota2.com/research/paper/69311572d6b0dd3342933a6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cc1e209131cea4d38e.md>)

[Implementation](<https://github.com/noahshinn024/reflexion>)

Recorded evaluation configuration: {"Agent Approach":"Reflexion","Model":"gpt-oss-20b"}. This record does not assert independent reproduction.

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