reasoning benchmark
PresentBench
PresentBench evaluates AI agents on producing presentation-style deliverables, such as generating lesson-plan slides and structured documents from source materials.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
PresentBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 54.6% | 100.0% | 2 | C | |
| 2 | BY | 48.3% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
PresentBench highlights
The top published results on this benchmark's own scale.
What is PresentBench?
Definition and scoring fields from the benchmark registry.
PresentBench evaluates AI agents on producing presentation-style deliverables, such as generating lesson-plan slides and structured documents from source materials.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- PresentBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- presentbench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about PresentBench.
Which model scores highest on PresentBench?
Seed 2.1 Pro is currently ranked first with 54.6%.
What does PresentBench measure?
PresentBench evaluates AI agents on producing presentation-style deliverables, such as generating lesson-plan slides and structured documents from source materials.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.