Is the ARC-AGI-3 score with their custom harness? I'm guessing that is what the footnote is for? (per https://openai.com/index/how-two-settings-tripled-our-arc-ag...)

> Performance is significantly higher than Fable 5.1

That's not clear. Need to see independent benchmarks first.

The annotation on arc-agi-3 is this: > OpenAI's own evaluation notes say Astra uses the company's Responses API harness, while comparison models can operate under different configurations.

With this configuration gpt-5.6-sol was able to reach 38,3%. So this is misleading.

any benchmark where opus 5 achieves higher scores than fable 5 in any way is not a benchmark worth trusting.

100% on ExploitBench seems fitting given recent events.

I think we need a few writing related benchmarks.