Examenos

Side-by-side · up to 5 models · official vs independent kept separate

— …

Choose up to five models to compare source-linked results. Official and independent scores stay separate. Browse model profiles or read the comparison guide. Interactive selection requires JavaScript.

    ▲ marks the best reported value in each row. Test setups can differ; open setup evidence for context. Shared links preserve your settings and show current published data.

    Selected models side by side: metadata, OpenRouter pricing, independent evaluators, and official benchmarks by category