Bard and gpt-oss-20b don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Bard shipped 868 days before gpt-oss-20b, so benchmark comparisons should account for the intervening progress.

Bard is proprietary, while gpt-oss-20b is open weight.

Direct benchmark comparisons are unavailable — Bard and gpt-oss-20b don't publish scores on any of the same benchmarks.