Open-weight models lag far behind on a triage test, with Llama 3.3 70B near zero
zakkohane · x · 2026-07-23
The same triage study also found a sharp gap for open-weight models on the harder cases.
- Llama 3.3 70B scored κ = 0.03 overall, 0.13 on easy pairs, and below zero on hard pairs.
- GLM-4.7 reached 0.24, and Kimi K2-Thinking scored 0.35.
- The author’s takeaway: the best open-weight model here is only about where the closed frontier was back in 2024.
Related event: Clinical Triage Retest: Closed-Source Models Far Outperform Open-Source(6 posts)→
More from Models
- Steve Hsu on OpenAI's Navier-Stokes paper: 'maybe beyond what a human could have come up with' — LucaAmb · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27