ProfBench (Search)
ProfBench (Search) - agentic search benchmark.
Category
General Agents
Score type
percent
Scale
100%
higher is better
Models tested
4
What is ProfBench (Search)?
ProfBench (Search) is a benchmark for how well a model acts as a general-purpose agent. The official description says: "ProfBench (Search) - agentic search benchmark". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
ProfBench (Search) measures how well a model acts as a general-purpose agent. In detail, it checks:
- solving long, multi-step tasks with many intermediate decisions
- using tools correctly (browsers, terminals, APIs, calendars, other apps)
- adapting when something unexpected happens mid-task
- staying on goal over long task horizons instead of wandering off
How to read the score
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Official methodology note: ProfBench (Search) - agentic search benchmark.
Frequently asked questions
What is the ProfBench (Search) benchmark?
ProfBench (Search) is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'ProfBench (Search) - agentic search benchmark'. Below we describe in simple words what benchmarks of this type generally examine.
What does ProfBench (Search) test?
ProfBench (Search) mainly measures how well a model acts as a general-purpose agent. Concretely, it checks: solving long, multi-step tasks with many intermediate decisions; using tools correctly (browsers, terminals, APIs, calendars, other apps); adapting when something unexpected happens mid-task.
How is the ProfBench (Search) score calculated?
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.
Where do I get ProfBench (Search) data and scores?
The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/profbench-search/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Benchmark dataset
The question/task data itself — download and evaluate locally
Benchmark metadata (JSON)
This page's benchmark record from the Open LLM Radar API
All model scores (JSON download)
Full score table as JSON; paginate with limit/offset params
Open LLM Radar API docs
Swagger UI to explore and reuse all radar API endpoints
Model scores 4 models tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
DeepSeek-V4-Pro
DeepSeek
|
59.9%
|
04.06.2026 | Report | Unverified |
| 2 |
DeepSeek-V4-Flash
DeepSeek
|
57%
|
04.06.2026 | Report | Unverified |
| 3 |
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
NVIDIA
|
56%
|
04.06.2026 | Report | Verified |
| 4 |
Kimi K2.6
Moonshot AI
|
56%
|
04.06.2026 | Report | Unverified |