DeepSeek V3 (Dec '24) vs HyperNova 60B 2605
Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek or HyperNova 60B 2605 by Multiverse Computing? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-07.
Trade-off
Verdict
Depends on your budget
HyperNova 60B 2605 scores 4.1 points higher (18.3 vs 14.2) but costs 1.9× as much to run the benchmark ($37.5 vs $20.0; both budget class). Pick HyperNova 60B 2605 when the extra intelligence is worth the premium, otherwise DeepSeek V3 (Dec '24).
| Metric | DeepSeek V3 (Dec '24) | HyperNova 60B 2605 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 14.2 | 18.3 | +28.9% HyperNova 60B 2605 is 28.9% more intelligent |
| Total AA cost (lower is better) | $20.02 | $37.50 | +87.3% HyperNova 60B 2605 is 87.3% more expensive |
| End-to-end time (lower is better) | Not reported | 6.93s | — not comparable |
| Price per 1M tokens (in / out) | $0.36 / $0.89 | $0.04 / $0.14 | |
| Input modalities | Not reported | Not reported |
HyperNova 60B 2605 vs DeepSeek V3 (Dec '24): 28.9% more intelligence, 87.3% more cost to run the AA benchmark, and end-to-end time not fully reported.
Today's Pareto frontier
Against the frontier
- DeepSeek V3 (Dec '24) is off the frontier: at the same or lower cost, GPT-5.6 Luna (low) scores 33.90 for $13.7.
- HyperNova 60B 2605 is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.1.
DeepSeek V3 (Dec '24)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-v3/hypernova-60b · Markdown: /api/v1/compare/deepseek-v3/hypernova-60b?format=md · llms.txt · agent skill