Lech Mazur(@LechMazur):New results on the Extended NYT Connections Benchmark: GPT-6.1 Sol (high) improves on GPT-6 Sol (high): 90.1 → 95.5, while costing about 54% less per puzzle. Claude Sonnet 5.5 (high) improves on Sonnet 5 (high): 75.1 → 80.5, while costing about 87% less per puzzle. Mistral Large 4 (high) improves on the non-reasoning Mistral Large 3: 7.5 → 27.4, but costs much more. More info:

Lech Mazur

@LechMazur

CEO, Advameg, Inc. founder Author: Author: 16 LLM benchmarks

加入 April 2009

465 正在关注 32.7K 粉丝

Lech Mazur@LechMazur

2026.10.07 23:13

New results on the Extended NYT Connections Benchmark: GPT-6.1 Sol (high) improves on GPT-6 Sol (high): 90.1 → 95.5, while costing about 54% less per puzzle. Claude Sonnet 5.5 (high) improves on Sonnet 5 (high): 75.1 → 80.5, while costing about 87% less per puzzle. Mistral Large 4 (high) improves on the non-reasoning Mistral Large 3: 7.5 → 27.4, but costs much more. More info:

显示更多