Claude Sonnet 5.5 and GPT-6 Astra tie at 41.7% on medical benchmark via opposite strengths
ArtificialAnlys · x · 2026-10-21
MLCR-AA requires both completeness and accuracy. Claude Opus 5.5 (max with fallback) reaches 63.3% completeness at just 37.2% accuracy; GPT-6.1 Sol (max) hits 96.7% accuracy at 40.0% completeness.
The co-leaders get to 41.7% differently: Claude Sonnet 5.5 (max with fallback) via 64.8% completeness and 60.9% accuracy, GPT-6 Astra (max) via 95.6% accuracy and 42.2% completeness.
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