token.app › Compare › GPT-5 Nano vs gpt-oss-120b
GPT-5 Nano vs gpt-oss-120b
gpt-oss-120b leads on 3 of 3 shared benchmarks. gpt-oss-120b is 2.0× cheaper per token on a blended 3:1 basis. GPT-5 Nano accepts the larger context window (400K).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-5 Nano | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Input $/1M | $0.050 | $0.037 |
| Output $/1M | $0.400 | $0.170 |
| Blended $/1M | $0.138 | $0.070 |
| Context window | 400K | 131K |
| Max output | 128K | 131K |
| Released | Aug 2025 | Aug 2025 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 69.4% | 75.8% |
| SimpleQA Verified | 12.2% | 13.9% |
| OTIS Mock AIME | 81.1% | 88.9% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose GPT-5 Nano if…
- Larger context window (400K)
- Newer model (released Aug 2025)
Choose gpt-oss-120b if…
- Costs less per token — $0.070 vs $0.138 blended
- Higher GPQA Diamond (75.8% vs 69.4%)
- Higher SimpleQA Verified (13.9% vs 12.2%)
- Higher OTIS Mock AIME (88.9% vs 81.1%)
- Open weights — self-hostable
FAQ
Which is better, GPT-5 Nano or gpt-oss-120b?
Across the 3 benchmarks both models have independently-run scores for, GPT-5 Nano leads on 0 and gpt-oss-120b leads on 3. Benchmarks are one input — price and context window are on this page too.
Is GPT-5 Nano cheaper than gpt-oss-120b?
gpt-oss-120b is cheaper: $0.070 versus $0.138 per million tokens blended at 3:1 input:output. Input alone: $0.050 vs $0.037. Output alone: $0.400 vs $0.170.
What context windows do GPT-5 Nano and gpt-oss-120b have?
GPT-5 Nano: 400,000 tokens. gpt-oss-120b: 131,072 tokens.
Who makes GPT-5 Nano and gpt-oss-120b?
GPT-5 Nano is made by OpenAI. gpt-oss-120b is made by OpenAI.