Artificial Analysis has released its fifth iteration of the Intelligence Index, a composite measure of AI model capabilities. This new version, v5, incorporates two new benchmarks and three upgraded evaluation datasets, with 60% of its assessments now utilizing private datasets. The index highlights Claude Opus 5.5 as the leading model, followed closely by OpenAI's GPT-6 Astra and GPT-6.1 Sol. The gap between leading proprietary models and open-weight models has also widened significantly. AI
IMPACT This new index provides a more comprehensive evaluation of AI models, particularly in coding and scientific research, potentially guiding future development and adoption.
RANK_REASON Release of a new benchmark index for AI models.
- Artificial Analysis Intelligence Index
- Enterococcus faecalis V583
- AA-Briefcase
- AA-Omniscience v1.1
- Anthropic
- Artificial Analysis Intelligence Index v5
- Artificial Analysis Progress Index v1
- AutomationBench-AA
- Claude Opus 5.5
- CritPt v2
- FrontierCode 2.0
- GDP.pdf
- Gemini 4 Argon
- GPT-6.1 Sol
- GPT-6 Astra
- HLE-Diamond
- OpenAI
- Terminal-Bench-Science
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →