knowledge benchmark
ProfBench Leaderboard
ProfBench evaluates models on professional-domain reasoning and knowledge-work tasks, including search-augmented question answering across expert fields.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
ProfBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelNV | Score56.00% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelIB | Score42.90% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelIB | Score41.20% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelIB | Score32.10% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
ProfBench Highlights
The leading models and scores on this benchmark.
ProfBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for ProfBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is ProfBench?
What ProfBench measures and how its scores work.
ProfBench is a knowledge benchmark for evaluating models on professional-domain reasoning and knowledge-work tasks.
It measures performance using the Score metric, reported as a ratio, on professional-domain reasoning, knowledge-work tasks, and search-augmented question answering across expert fields.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ProfBench
- Modality
- text
- Primary category
- knowledge
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ProfBench.
Which model scores highest on ProfBench?
Nemotron 3 Ultra (550B A55B) is currently ranked first with 56.00%.
What are the top three models on ProfBench?
The current leaders are Nemotron 3 Ultra (550B A55B) (56.00%), IBM Granite 4.2 30B (42.90%), and IBM Granite 4.2 8B (41.20%).
Which ProfBench model has the lowest official input price?
Nemotron 3 Ultra (550B A55B) has the lowest matched official input price at $0.50 input / $2.5 output per 1M tokens.
Which models are fastest among ProfBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.