GLM-5.2 (Max) vs GPT-5 mini (High)
Which is better for the money: GLM-5.2 (Max) by Z AI or GPT-5 mini (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
GLM-5.2 (Max) scores 16.9 points higher (33.7 vs 16.8) but costs 11× as much to run the benchmark ($2097 vs $189; flagship vs mid-range cost classes). They are not alternatives at one budget: pick GLM-5.2 (Max) when you need intelligence above 16.8, and GPT-5 mini (High) when 16.8 is enough.
| Metric | GLM-5.2 (Max) | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 33.7 | 16.8 | −50.1% GPT-5 mini (High) is 50.1% less intelligent |
| Total AA cost (lower is better) | $2,097.29 | $188.66 | −91.0% GPT-5 mini (High) is 91.0% cheaper |
| End-to-end time (lower is better) | 29.25s | 58.72s | +100.8% GPT-5 mini (High) is 100.8% slower |
| Price per 1M tokens (in / out) | $1.40 / $4.40 | $0.25 / $2.00 | |
| Input modalities | Text | Text, Image |
GPT-5 mini (High) vs GLM-5.2 (Max): 50.1% less intelligence, 91.0% less cost to run the AA benchmark, and 100.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GLM-5.2 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
GLM-5.2 (Max)GPT-5 mini (High)Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/glm-5-2/gpt-5-mini · Markdown: /api/v1/compare/glm-5-2/gpt-5-mini?format=md · llms.txt · agent skill