Tester claims GPT-6 Sol is 6–7x faster than Astra at same thinking settings
A self-described hands-on test post claims GPT-6-sol is 6–7 times faster than Astra at the same thinking settings, and also comments on Opus 5.5, Grok 4.7 and Gemini 4 Pro.
Tested by me > Unfortunately, token efficiency has dropped again for opus 5.5 > OpenAI "bel" is perceived as AGI by them > Grok 4.7 is dead on arrival > GPT-6-sol is 6-7 times more faster compared to astra on same thinking settings > Gemini 4 pro is back in the game with insane webdev , 3d and spatial reasoning ( its the same lead that 2.5 pro had on sonnet 3.5 and gpt o3) Leaks : anthropic model 3 is in training already it is there answer to bel , we had model 2 charts in august which scores 10% higher then current mythos 5.1 use this perspective gpt astra max intelligence is dumb than bel low intelligence with an degree of margin this is not seen by any model jump yet in openai < last was opus 4.8 to mythos 5 by ant>