general benchmark
Artificial Analysis
Artificial Analysis benchmark evaluates AI models across quality, speed, and pricing dimensions, providing a composite assessment of model capabilities for real-world usage.
Updated Aug 7, 2026
Published models5
Registry coverage5
MetricScore
EvidenceB
Artificial Analysis leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 59.0% | 100.0% | 5 | B | |
| 2 | OP | 55.0% | 75.0% | 5 | B | |
| 3 | XA | 54.0% | 50.0% | 5 | B | |
| 4 | OP | 51.0% | 25.0% | 5 | B | |
| 5 | MI | 50.0% | 0.0% | 5 | C |
Score distribution
Top published rows on the benchmark's original scale.
Artificial Analysis highlights
The top published results on this benchmark's own scale.
What is Artificial Analysis?
Definition and scoring fields from the benchmark registry.
Artificial Analysis benchmark evaluates AI models across quality, speed, and pricing dimensions, providing a composite assessment of model capabilities for real-world usage.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Artificial Analysis
- Modality
- text
- Primary category
- general
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- artificial-analysis|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Artificial Analysis.
Which model scores highest on Artificial Analysis?
GPT-5.6 Sol is currently ranked first with 59.0%.
What does Artificial Analysis measure?
Artificial Analysis benchmark evaluates AI models across quality, speed, and pricing dimensions, providing a composite assessment of model capabilities for real-world usage.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
5 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.