Public ranking sources
Artificial Analysis AI model ranking data
OpenGPT preserves 7 published Artificial Analysis records in their original source scope. It does not rerun or blend this ranking with another benchmark.
- Published records
- 7
- Ranking views
- Intelligence Index
- Source data date
- Retrieved
Evidence scope
Intelligence Index v4.1.1 · rolling results. Nine evaluations across agentic work, coding, general knowledge, and scientific reasoning.
How OpenGPT handles this evidence
OpenGPT stores the publisher's labels, positions, configurations, dates, and values within the same published scope. It does not convert missing values to zero or merge this source into a cross-source score.
Comparison boundaries
- Ranks and values are comparable only inside the named source release and ranking scope.
- A source-listed configuration is linked to an official model ID only when identity evidence has been reviewed.
- Published rankings are screening signals; production choice still requires testing the exact version on real work.
Intelligence Index v4.1.1
Showing 6 representative rows from 7 published records. Follow a row to inspect its exact source identity and mapping evidence.
- Claude Opus 5Anthropic · Intelligence Index#163Max effort
- Claude Opus 5Anthropic · Intelligence Index#263xHigh effort
- Claude Fable 5Anthropic · Intelligence Index#362Opus 4.8 fallback
- Claude Opus 5Anthropic · Intelligence Index#461High effort
- GPT-5.6 SolOpenAI · Intelligence Index#561Max effort
- Kimi K3Kimi · Intelligence Index#660Max effort