Verdict
Built from the measurements below
- Accuracy is too close to call: gpt-oss-20b scored 51.2% and Nemotron 3.5 Lightning 43.8% on the same 80 questions, a gap within what chance alone could produce.
- gpt-oss-20b is 7.4× cheaper per question as billed ($0.000066 vs $0.00049), reasoning tokens included.
- Nemotron 3.5 Lightning generates text 1.1× faster: 116 tokens per second against 103.
- Nemotron 3.5 Lightning starts answering sooner: 0.5 s to the first token, against 0.7 s for gpt-oss-20b.
- Nemotron 3.5 Lightning accepts more context: 262k tokens against 131k.
Which should you choose?
Choose gpt-oss-20b for the lower cost per correct answer ($0.00013 against $0.0011), shorter outputs (about 472 tokens per question against 2,846) and more hosts to choose from on OpenRouter (10 against 4). Choose Nemotron 3.5 Lightning for faster streaming, a quicker first token and a 262k-token context window.
Accuracy gap +7.5 points (z = 0.95). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.