Devstral Small and GLM-4 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4 shipped 491 days before Devstral Small, so benchmark comparisons should account for the intervening progress.

Devstral Small is open weight, while GLM-4 is proprietary.

Direct benchmark comparisons are unavailable — Devstral Small and GLM-4 don't publish scores on any of the same benchmarks.