DeepSeek V4 Pro (Reasoning, Max Effort) vs HyperNova 60B 2605
Which is better for the money: DeepSeek V4 Pro (Reasoning, Max Effort) by DeepSeek or HyperNova 60B 2605 by Multiverse Computing? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-07-18.
Trade-off
Verdict
Depends on your budget
DeepSeek V4 Pro (Reasoning, Max Effort) scores 26.5 points higher (44.3 vs 17.8) but costs 5.0× as much to run the benchmark ($176 vs $35.0; mid-range vs budget cost classes). They are not alternatives at one budget: pick DeepSeek V4 Pro (Reasoning, Max Effort) when you need intelligence above 17.8, and HyperNova 60B 2605 when 17.8 is enough.
| Metric | DeepSeek V4 Pro (Reasoning, Max Effort) | HyperNova 60B 2605 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 44.3 | 17.8 | −59.8% HyperNova 60B 2605 is 59.8% less intelligent |
| Total AA cost (lower is better) | $176.34 | $35.05 | −80.1% HyperNova 60B 2605 is 80.1% cheaper |
| End-to-end time (lower is better) | 80.52s | 7.98s | −90.1% HyperNova 60B 2605 is 90.1% faster |
| Price per 1M tokens (in / out) | $0.43 / $0.87 | $0.04 / $0.14 | |
| Input modalities | Not reported | Not reported |
HyperNova 60B 2605 vs DeepSeek V4 Pro (Reasoning, Max Effort): 59.8% less intelligence, 80.1% less cost to run the AA benchmark, and 90.1% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro (max) is on today's frontier: nothing is both smarter and cheaper.
- HyperNova 60B 2605 is off the frontier: at the same or lower cost, MiMo-V2.5 scores 37.20 for $25.2.
DeepSeek V4 Pro (Reasoning, Max Effort)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/deepseek-v4-pro/hypernova-60b · Markdown: /api/v1/compare/deepseek-v4-pro/hypernova-60b?format=md · llms.txt · agent skill