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 2026-07-17.
Depends on your budget
Claude Sonnet 5 (Non-reasoning, High Ef… scores 23.9 points higher (41.7 vs 17.8) but costs 12× as much to run the benchmark ($427 vs $35.0; 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 17.8, and HyperNova 60B 2605 when 17.8 is enough.
| Metric | Claude Sonnet 5 (Non-reasoning, High Effort) | HyperNova 60B 2605 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 41.7 | 17.8 | −57.3% HyperNova 60B 2605 is 57.3% less intelligent |
| Total AA cost (lower is better) | $427.33 | $35.05 | −91.8% HyperNova 60B 2605 is 91.8% cheaper |
| End-to-end time (lower is better) | 9.27s | 8.32s | −10.2% HyperNova 60B 2605 is 10.2% 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): 57.3% less intelligence, 91.8% less cost to run the AA benchmark, and 10.2% 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 Sol (low) scores 49.40 for $353.
- HyperNova 60B 2605 is off the frontier: at the same or lower cost, MiMo-V2.5 scores 37.20 for $25.2.
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