The most prestigious law school admissions discussion board in the world.
|
 |
 
|
gpt-6 saturates the frontier math and arc-agi 3 metrics
| The Penis | 09/04/26 |
Poast new message in this thread
Date: September 4th, 2026 2:26 AM Author: The Penis 99.9%. gpt-6-astra 30.2%. claude-opus-5 7.8%. gpt 5.6 sol
ARC-AGI-3 tests how well agents learn as they solve unfamiliar interactive tasks. GPT‑6 Astra saturates the eval, scoring 99.9%. The average human tester scored 48%. GPT‑6 Astra was measured with our responses API harness, which better reflects real-world performance than the original benchmark harness, which discards past reasoning and past messages. With this harness, we estimate Sol would score in the ballpark of ~30% |