Anthropic sweeps medical benchmark completeness top 18, Sonnet 5.5 leads at 64.8%
ArtificialAnlys · x · 2026-10-21
On Artificial Analysis' MLCR-AA completeness dimension, Claude models hold the top 18 scores across every model and effort level. 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 just 42.2%.
Completeness means covering every key point of the expert reference answer, including the conclusion and the gaps in the record the expert reasons from.
More from Models
- Recursive AI ships Flint, a 40B-A2.5B MoE claimed to match Qwen3.6-27B, weights on Hugging Face — ChengleiSi · 2026-10-22
- DeepSeek ships V4.1-Flash-1017, now the #1 open model on RSI-Inference Bench — scaling01 · 2026-10-22
- OpenAI's Cybersecurity Guardrails Block a Dev From Auditing His Own Patched Server — Next_Technology6361 · 2026-10-22
- TPN-006 hits Hugging Face: 7.7GB compressed model beats its 17GB Mistral teacher — markjeffrey · 2026-10-22
- Kimi K3.1's latest checkpoint draws 49k-token SVG portrait zero-shot in 22 minutes — lyraxana · 2026-10-22
- MiniMax launches M3.1 Flash at 1/3 the cost and 3x the speed of M3, weights out Oct 23 — MiniMax_AI · 2026-10-22