The most prestigious law school admissions discussion board in the world.
|
 |
 
|
Introducing Claude Opus 5.5
| The Penis | 09/22/26 |
| .,.,...,..,.,.,:,,:,.,.,:::,...,:,...:..:.,:.::,. | 09/22/26 |
| The Penis | 09/22/26 |
| .,.,...,..,.,.,:,,:,.,.,:::,...,:,...:..:.,:.::,. | 09/22/26 |
Poast new message in this thread
Date: September 22nd, 2026 12:33 PM Author: The Penis (http://www.autoadmit.com/thread.php?thread_id=5905936&forum_id=2,#50149277) |
Date: September 22nd, 2026 12:44 PM Author: .,.,...,..,.,.,:,,:,.,.,:::,...,:,...:..:.,:.::,. Oh shit, not flame. The craziest part is that it beats Fable on everything (I got the chart from Opus 5.5):
Benchmark Opus 5.5 Fable 5.1 Opus 5 Terminal-Bench 4.0 (agentic coding) 66.4% 55.8% 52.3% FrontierCode v1.1 Main (coding) 54.4% 50.3% 48.0% CursorBench 4.0 (coding) 57.8% 51.8% 46.6% GDPval-AA v2.1 (knowledge work, Elo) 1846 1735 1708 AutomationBench (business workflows) 40.0% 31.4% 26.9% Humanity's Last Exam (with tools) 67.7% 65.6% 63.6% Terminal-Bench-Science 0.1 58.7% 52.6% 29.0% OSWorld 2.0 (computer use) 81.8% 80.7% 74.0% Chartography (chart reading) 89.0% 88.4% 83.4% Price per 1M tokens (input / output) $4 / $20 $10 / $50 $5 / $25 |
 |
Date: September 22nd, 2026 12:48 PM Author: The Penis Yeah much cheaper too. I think it said 40%. Pretty crazy. Wonder what Fable 5.5 is like, I'd bet they already have it running internally. (http://www.autoadmit.com/thread.php?thread_id=5905936&forum_id=2,#50149309) |
|
Date: September 22nd, 2026 12:54 PM Author: .,.,...,..,.,.,:,,:,.,.,:::,...,:,...:..:.,:.::,. Wouldn't make sense for it not to leapfrog Opus 5.5. (http://www.autoadmit.com/thread.php?thread_id=5905936&forum_id=2,#50149330) |