GLM-4.7 (Reasoning) vs HyperNova 60B 2605
Which is better for the money: GLM-4.7 (Reasoning) by Z AI or HyperNova 60B 2605 by Multiverse Computing? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-07.
Trade-off
Verdict
Depends on your budget
GLM-4.7 (Reasoning) scores 16.2 points higher (34.5 vs 18.3) but costs 16× as much to run the benchmark ($607 vs $37.5; premium vs budget cost classes). They are not alternatives at one budget: pick GLM-4.7 (Reasoning) when you need intelligence above 18.3, and HyperNova 60B 2605 when 18.3 is enough.
| Metric | GLM-4.7 (Reasoning) | HyperNova 60B 2605 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.5 | 18.3 | −47.0% HyperNova 60B 2605 is 47.0% less intelligent |
| Total AA cost (lower is better) | $607.19 | $37.50 | −93.8% HyperNova 60B 2605 is 93.8% cheaper |
| End-to-end time (lower is better) | 27.02s | 6.93s | −74.4% HyperNova 60B 2605 is 74.4% faster |
| Price per 1M tokens (in / out) | $0.60 / $2.20 | $0.04 / $0.14 | |
| Input modalities | Not reported | Not reported |
HyperNova 60B 2605 vs GLM-4.7 (Reasoning): 47.0% less intelligence, 93.8% less cost to run the AA benchmark, and 74.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GLM-4.7 (Reasoning) is off the frontier: at the same or lower cost, Grok 4.5 (high) scores 55.80 for $579.
- HyperNova 60B 2605 is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.1.
GLM-4.7 (Reasoning)HyperNova 60B 2605Today's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/glm-4-7/hypernova-60b · Markdown: /api/v1/compare/glm-4-7/hypernova-60b?format=md · llms.txt · agent skill