reasoning benchmark
WideSearch
WideSearch is an agentic search benchmark that evaluates models' ability to perform broad, parallel search operations across multiple sources. It tests wide-coverage information retrieval and synthesis capabilities.
Updated Aug 11, 2026
Models9
Model coverage9
MetricScore
EvidenceB
WideSearch Ranking
Higher score ranks better on this benchmark.
| 01 | MA | 80.8% | 100.0% | 9 | C | |
| 02 | MA | 79.0% | 87.5% | 9 | C | |
| 03 | TE | 76.4% | 75.0% | 9 | C | |
| 04 | AC | 74.3% | 62.5% | 9 | C | |
| 05 | AC | 74.0% | 50.0% | 9 | C | |
| 06 | AC | 61.1% | 37.5% | 9 | C | |
| 07 | AC | 60.5% | 25.0% | 9 | C | |
| 08 | AC | 60.1% | 12.5% | 9 | C | |
| 09 | AC | 57.1% | 0.0% | 9 | C |
WideSearch Score Distribution
A closer view of the leading scores on this benchmark.
WideSearch Highlights
The leading models and scores on this benchmark.
What is WideSearch?
What WideSearch measures and how its scores work.
WideSearch is an agentic search benchmark that evaluates models' ability to perform broad, parallel search operations across multiple sources. It tests wide-coverage information retrieval and synthesis capabilities.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- WideSearch
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- widesearch|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about WideSearch.
Which model scores highest on WideSearch?
Kimi K2.6 is currently ranked first with 80.8%.
What does WideSearch measure?
WideSearch is an agentic search benchmark that evaluates models' ability to perform broad, parallel search operations across multiple sources. It tests wide-coverage information retrieval and synthesis capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
9 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.