General Agents Benchmark

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.

Model scores 4 models tested

Reset
# 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

What now?

You've seen how models score on ProfBench (Search) — here's what to do next.