Claude Sonnet 5 (Non-reasoning, High Effort) vs HyperNova 60B 2605
Which is better for the money: Claude Sonnet 5 (Non-reasoning, High Effort) by Anthropic 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.
Depends on your budget
Claude Sonnet 5 (Non-reasoning, High Ef… scores 24.3 points higher (42.6 vs 18.3) but costs 11× as much to run the benchmark ($416 vs $37.5; mid-range vs budget cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (Non-reasoning, High Ef… when you need intelligence above 18.3, and HyperNova 60B 2605 when 18.3 is enough.
| Metric | Claude Sonnet 5 (Non-reasoning, High Effort) | HyperNova 60B 2605 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 42.6 | 18.3 | −57.0% HyperNova 60B 2605 is 57.0% less intelligent |
| Total AA cost (lower is better) | $415.75 | $37.50 | −91.0% HyperNova 60B 2605 is 91.0% cheaper |
| End-to-end time (lower is better) | 10.06s | 6.93s | −31.1% HyperNova 60B 2605 is 31.1% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.04 / $0.14 | |
| Input modalities | Not reported | Not reported |
HyperNova 60B 2605 vs Claude Sonnet 5 (Non-reasoning, High Effort): 57.0% less intelligence, 91.0% less cost to run the AA benchmark, and 31.1% faster end-to-end.
Against the frontier
- Claude Sonnet 5 (non-reasoning, high) is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
- HyperNova 60B 2605 is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.1.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-sonnet-5-non-reasoning/hypernova-60b · Markdown: /api/v1/compare/claude-sonnet-5-non-reasoning/hypernova-60b?format=md · llms.txt · agent skill