HyperNova 60B 2605 vs Inkling (xhigh)
Which is better for the money: HyperNova 60B 2605 by Multiverse Computing or Inkling (xhigh) by Thinking Machines? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-09-01.
Trade-off
Verdict
Depends on your budget
Inkling (xhigh) scores 24.0 points higher (42.3 vs 18.3) but costs 19× as much to run the benchmark ($698 vs $37.5; premium vs budget cost classes). They are not alternatives at one budget: pick Inkling (xhigh) when you need intelligence above 18.3, and HyperNova 60B 2605 when 18.3 is enough.
| Metric | HyperNova 60B 2605 | Inkling (xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 18.3 | 42.3 | +131.1% Inkling (xhigh) is 2.3× more intelligent |
| Total AA cost (lower is better) | $37.50 | $698.28 | +1762.1% Inkling (xhigh) is 19× more expensive |
| End-to-end time (lower is better) | 8.08s | 35.03s | +333.5% Inkling (xhigh) is 333.5% slower |
| Price per 1M tokens (in / out) | $0.04 / $0.14 | $1.00 / $4.05 | |
| Input modalities | Not reported | Not reported |
Inkling (xhigh) vs HyperNova 60B 2605: 131.1% more intelligence, 1762.1% more cost to run the AA benchmark, and 333.5% slower end-to-end.
Today's Pareto frontier
Against the frontier
- HyperNova 60B 2605 is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.5.
- Inkling (xhigh) is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 57.50 for $138.
HyperNova 60B 2605Inkling (xhigh)Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/hypernova-60b/inkling · Markdown: /api/v1/compare/hypernova-60b/inkling?format=md · llms.txt · agent skill