Gemma 4 31B (Non-reasoning) vs HyperNova 60B 2605
Which is better for the money: Gemma 4 31B (Non-reasoning) by Google 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.
Clear winner
Verdict
Pick Gemma 4 31B (Non-reasoning)
HyperNova 60B 2605 vs Gemma 4 31B (Non-reasoning): 17.9% less intelligence, 14.3% more cost to run the AA benchmark, and 32.7% faster end-to-end.
| Metric | Gemma 4 31B (Non-reasoning) | HyperNova 60B 2605 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 22.3 | 18.3 | −17.9% HyperNova 60B 2605 is 17.9% less intelligent |
| Total AA cost (lower is better) | $32.80 | $37.50 | +14.3% HyperNova 60B 2605 is 14.3% more expensive |
| End-to-end time (lower is better) | 10.29s | 6.93s | −32.7% HyperNova 60B 2605 is 32.7% faster |
| Price per 1M tokens (in / out) | $0.15 / $0.40 | $0.04 / $0.14 | |
| Input modalities | Not reported | Not reported |
Today's Pareto frontier
Against the frontier
- Gemma 4 31B (Non-reasoning) is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.1.
- HyperNova 60B 2605 is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.1.
Gemma 4 31B (Non-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/gemma-4-31b-non-reasoning/hypernova-60b · Markdown: /api/v1/compare/gemma-4-31b-non-reasoning/hypernova-60b?format=md · llms.txt · agent skill