OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3 with its latest API and two additional settings
By Matthias Bastian
AI 摘要
OpenAI counters Anthropic's ARC-AGI-3 record: GPT-5.6 Sol scores 38.3 percent, but only with its own API features instead of the official test setup, where the model landed at 7.8 percent. ARC Prize claims its test environment is provider-neutral, but may have used an outdated API that skewed the co
原文正文
OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3 with its latest API and two additional settings
Update –
- Added ARC Prize statements
Update:
ARC Prize co-founder François Chollet responded to OpenAI's results by distinguishing between two kinds of test setups. Harnesses "custom-made to solve the benchmark or that contain knowledge about the benchmark format" are off limits, he said. General-purpose API settings "that were not developed for ARC-AGI-3 and that are available to all API users" are fair game. In effect, Chollet is conceding that ARC Prize's own GPT-5.6 Sol score put OpenAI at a disadvantage.
He noted that ARC Prize has had "a lot of back and forth with OpenAI about how to best test their models, especially with regard to compaction," and welcomed the company "starting to figure out the answer." Different providers using different settings does create "a potential parity issue," Chollet said, but he considers that acceptable "as long as the settings and the cost are clearly reported."
Original article:
OpenAI says it can keep up on ARC-AGI-3. After Anthropic's Claude Opus 5 quadrupled the record score on the logic benchmark, OpenAI is now showing that GPT-5.6 Sol hits 38.3 percent with two API settings, beating Opus 5's 30.2 percent.
OpenAI isn't using the official test environment, though. Instead, it runs GPT-5.6 Sol through its own Responses API with "Retained Reasoning," which keeps the model's chain of thought between steps, and "Compaction," which summarizes old context instead of truncating it. In the official harness, GPT-5.6 Sol scored just 7.8 percent because the model's reasoning gets discarded after each action.
OpenAI argues that benchmarks never measure just the model but also the technical setup around it. That's true, and ARC-AGI-3 is designed to test pure model performance. The official ARC scores use a standardized approach without provider-specific settings to ensure fair comparisons, ARC Prize said in response to OpenAI's results. The sticking point is whether ARC Prize used an older "OpenAI-style completions API" that lacked features the Claude API already offered, which would make the comparison unfair to OpenAI.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe now