# Web Search on HotpotQA (Latency and Cost)

Source: [Web Search on HotpotQA (Latency and Cost)](<https://www.sota2.com/research/sota/web-search-on-hotpotqa-latency-and-cost>)

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

Data updated: 2026-02-26T05:57:50.908Z

Evaluation of the Web Search component on the HotpotQA dataset, focusing on operational metrics such as performance latency and associated cost.

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 | Web Search |
| Dataset (including any stated split) | HotpotQA |
| Metric | Performance Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Performance Score](<https://www.sota2.com/research/sota/web-search-on-hotpotqa-latency-and-cost.md?metric=Performance%20Score>): Higher is better; unit: PERCENT.

- [Cost ($)](<https://www.sota2.com/research/sota/web-search-on-hotpotqa-latency-and-cost.md?metric=Cost%20(%24)>): Lower is better; unit: OTHER.

- [Delay (h)](<https://www.sota2.com/research/sota/web-search-on-hotpotqa-latency-and-cost.md?metric=Delay%20(h)>): Lower is better; unit: TIME.

## Recorded results

| Method | Performance Score | Result date | Report paper |
| --- | --- | --- | --- |
| MasRouter | 88.5 | Not recorded | 695de87753fdd5c361743c7c |
| EvoRoute | 87.8 | Not recorded | 695de87753fdd5c361743c7c |
| Gemini-2.5-pro | 87.4 | Not recorded | 695de87753fdd5c361743c7c |
| GPT-4.1 | 87 | Not recorded | 695de87753fdd5c361743c7c |
| GraphRouter | 86.1 | Not recorded | 695de87753fdd5c361743c7c |
| PromptLLM | 85.2 | Not recorded | 695de87753fdd5c361743c7c |
| GPT-4o | 83.84 | Not recorded | 695de87753fdd5c361743c7c |
| Qwen3-14b | 81.4 | Not recorded | 695de87753fdd5c361743c7c |

### MasRouter

Performance Score: 88.5. Result ID: 6996a2e35698665ec4ec708a.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fd1e209131cea7049b.md>)

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

### EvoRoute

Performance Score: 87.8. Result ID: 6996a2e35698665ec4ec708b.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

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

### Gemini-2.5-pro

Performance Score: 87.4. Result ID: 6996a2e35698665ec4ec7086.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

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

### GPT-4.1

Performance Score: 87. Result ID: 6996a2e35698665ec4ec7085.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

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

### GraphRouter

Performance Score: 86.1. Result ID: 6996a2e35698665ec4ec7089.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

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

### PromptLLM

Performance Score: 85.2. Result ID: 6996a2e35698665ec4ec7088.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

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

### GPT-4o

Performance Score: 83.84. Result ID: 6996a2e35698665ec4ec7084.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

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

### Qwen3-14b

Performance Score: 81.4. Result ID: 6996a2e35698665ec4ec7087.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

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

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