Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Hy3 | gpt-oss-120b (low) |
|---|---|---|
| Input ($/M tokens) | $0.136 | $0.15 |
| Output ($/M tokens) | $0.557 | $0.595 |
Verdict. gpt-oss-120b (low) takes the aggregate benchmark matchup 6–5 across 11 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 0.9× the per-million-token cost, Hy3 is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Hy3 makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Hy3 is strongest on GPQA Diamond (90%), Coding Index (58.8), SciCode (48%). gpt-oss-120b (low) leads on MMLU-Pro (78%), LiveCodeBench (71%), GPQA Diamond (67%).
Speed. On throughput, gpt-oss-120b (low) generates tokens at 275 tok/s versus 71 tok/s — about 74% faster. On time-to-first-token, gpt-oss-120b (low) responds in 558ms vs 1757ms, which matters most for chat-style UIs.
Provider. Tencent and OpenAI sell to overlapping but distinct developer audiences: Tencent tends to ship frontier reasoning models with premium positioning, while OpenAI 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): Hy3 costs $12.44 ($149/year); gpt-oss-120b (low) costs $13.43 ($161/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Hy3 ≈ $1.79/run, gpt-oss-120b (low) ≈ $1.94/run. At agent/realtime scale (200M input / 100M output per million requests): Hy3 ≈ $83/run, gpt-oss-120b (low) ≈ $90/run. Hy3 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.
Head-to-head deltas
Data from Artificial Analysis API — 12 benchmarks
Hy3 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.24/M tokens vs $0.26/M for gpt-oss-120b (low).
gpt-oss-120b (low) wins 6 out of 12 benchmarks compared to 5 for Hy3. See the detailed benchmark chart above for per-category results.
gpt-oss-120b (low) generates tokens faster at 275 tok/s vs 71 tok/s. However, gpt-oss-120b (low) has lower time-to-first-token (0.56s vs 1.76s).
Choose based on your priorities: Hy3 for lower cost, gpt-oss-120b (low) for stronger benchmark performance, and gpt-oss-120b (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.