Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Solar Mini | HyperNova 60B 2605 (high, based on gpt-oss-120b) |
|---|---|---|
| Input ($/M tokens) | $0.15 | $0.04 |
| Output ($/M tokens) | $0.15 | $0.14 |
Verdict. HyperNova 60B 2605 (high, based on gpt-oss-120b) takes the aggregate benchmark matchup 2–0 across 2 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.1× the per-million-token cost, HyperNova 60B 2605 (high, based on gpt-oss-120b) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). HyperNova 60B 2605 (high, based on gpt-oss-120b) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Solar Mini is strongest on Intelligence Index (6.0). HyperNova 60B 2605 (high, based on gpt-oss-120b) leads on Coding Index (23.2), Intelligence Index (18.3).
Speed. Speed data is incomplete for this pair; benchmark and price should decide.
Provider. Upstage and Multiverse Computing sell to overlapping but distinct developer audiences: Upstage tends to ship frontier reasoning models with premium positioning, while Multiverse Computing often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Solar Mini costs $6.75 ($81/year); HyperNova 60B 2605 (high, based on gpt-oss-120b) costs $3.30 ($40/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Solar Mini ≈ $1.05/run, HyperNova 60B 2605 (high, based on gpt-oss-120b) ≈ $0.48/run. At agent/realtime scale (200M input / 100M output per million requests): Solar Mini ≈ $45/run, HyperNova 60B 2605 (high, based on gpt-oss-120b) ≈ $22/run. HyperNova 60B 2605 (high, based on gpt-oss-120b) becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Data from Artificial Analysis API — 12 benchmarks
HyperNova 60B 2605 (high, based on gpt-oss-120b) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.07/M tokens vs $0.15/M for Solar Mini.
HyperNova 60B 2605 (high, based on gpt-oss-120b) wins 2 out of 12 benchmarks compared to 0 for Solar Mini. See the detailed benchmark chart above for per-category results.
HyperNova 60B 2605 (high, based on gpt-oss-120b) generates tokens faster at 350 tok/s vs — tok/s. However, HyperNova 60B 2605 (high, based on gpt-oss-120b) has lower time-to-first-token (0.79s vs —s).
Choose based on your priorities: HyperNova 60B 2605 (high, based on gpt-oss-120b) for lower cost, HyperNova 60B 2605 (high, based on gpt-oss-120b) for stronger benchmark performance, and HyperNova 60B 2605 (high, based on gpt-oss-120b) for faster generation. For latency-sensitive apps, check the TTFT comparison above.