Verdict
Built from the measurements below
- Accuracy is too close to call: gpt-oss-120b scored 58.8% and Hy3 58.8% on the same 80 questions, a gap within what chance alone could produce.
- gpt-oss-120b is 9.8× cheaper per question as billed ($0.00013 vs $0.0012), reasoning tokens included.
- Hy3 generates text 1.2× faster: 96 tokens per second against 82.
- gpt-oss-120b starts answering sooner: 0.5 s to the first token, against 1.7 s for Hy3.
- Hy3 accepts more context: 262k tokens against 131k.
Which should you choose?
Choose gpt-oss-120b for the lower cost per correct answer ($0.00021 against $0.0021), a quicker first token, shorter outputs (about 546 tokens per question against 2,355) and more hosts to choose from on OpenRouter (23 against 5). Choose Hy3 for faster streaming and a 262k-token context window. The widest subject gap is in law: Hy3 answered 4 of 6 correctly, gpt-oss-120b 1 of 6. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.
Accuracy gap +0.0 points (z = 0.00). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.