Topic: #benchmarks
-
Grok 4.7 ties MiMo-V2.6-Pro for first on Artificial Analysis Cyber Index
Grok 4.7 and MiMo-V2.6-Pro tied for first on Artificial Analysis's new Cyber Index with scores of 56, Crypto Briefing reported. Grok's $11.67 per-task cost was called high against cheaper rival models.
-
Ox Alpha Beats Claude and GPT on Benchmarks, Creator Unknown
A mystery AI model called Ox Alpha appeared on OpenRouter on August 20 with no company name attached. It beats Claude Fable 5 and GPT-5.6 Sol on coding benchmarks, reads 1 million tokens, accepts video input, and is free to use. Developers are guessing who built it.