Anthropic models lead on completeness: reaching the expert's conclusion with the right medical reasoning, demonstrating medical knowledge and reasoning ability.
An answer is complete when it covers every key point of the expert reference answer that the question asks for, including the conclusion and the gaps in the record that the expert reasons from. Claude models hold the top 18 completeness scores across every model and effort level we tested. Claude Sonnet 5.5 (max with fallback) leads at 64.8%, followed by Claude Opus 5.5 (max with fallback) at 63.3% and Claude Fable 5.1 (max with fallback) at 61.1%. The best non-Anthropic model is GPT-6 Astra (max) at 42.2%.
Anthropic models lead on completeness: reaching the expert's conclusion with the right medical reasoning, demonstrating medical knowledge…
Anthropic models lead on completeness: reaching the expert's conclusion with the right medical reasoning, demonstrating medical knowledge and reasoning ability. An answer is complete when it covers every key point of the expert reference answer that the question asks for, including the conclusion and the gaps in the record that the expert reasons from.
Artificial Analysis · X
Content notes
Original publication and rights belong to the source.