GLM 5.3 Flash
13th on DeepSWE v1.1 Best (max) at 63.4%, about $0.48 mean per task.
Zhipu · Proprietary · Fetched 2026-10-10
Benchmark scores
Boards older than 90 days are not counted as recommendationsBenchmarkSettingScoreRankCostAs of
Use it or not
Why
- Mid-front on DeepSWE, much cheaper per task than GLM 5.3 on that board.
When not
- A different row from GLM 5.3; use the full tier for heavier work.