OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3 but only with its own custom test harness

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 API (Chat Completions) 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