Cool multi-agent experiments in the 5.5 system card!
They're getting a solve rate of close to 100% on their subset of 166 ProgramBench instances (out of 200), so I think they're not using the tougher programs (FFmpeg, the PHP compiler, ...) since we're seeing a very low solve rate on those.
Multi-agent runs on ProgramBench in Opus 5.5 system card
Multi-agent systems get to the same outcomes as a single-agent, but quicker.
Worth noting that just 166/200 tasks were used. I still strongly encourage using all 200! The long tail of hard tasks is really difficult.