token.app › Compare › GPT-4o vs gpt-oss-120b
GPT-4o vs gpt-oss-120b
gpt-oss-120b leads on 2 of 2 shared benchmarks. gpt-oss-120b is 62× cheaper per token on a blended 3:1 basis. gpt-oss-120b accepts the larger context window (131K).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-4o | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Input $/1M | $2.50 | $0.037 |
| Output $/1M | $10.00 | $0.170 |
| Blended $/1M | $4.38 | $0.070 |
| Context window | 128K | 131K |
| Max output | 16K | 131K |
| Released | May 2024 | Aug 2025 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 47.9% | 75.8% |
| OTIS Mock AIME | 6.3% | 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-4o if…
- No clear advantage on the data we hold.
Choose gpt-oss-120b if…
- Costs less per token — $0.070 vs $4.38 blended
- Higher GPQA Diamond (75.8% vs 47.9%)
- Higher OTIS Mock AIME (88.9% vs 6.3%)
- Larger context window (131K)
- Open weights — self-hostable
- Newer model (released Aug 2025)
FAQ
Which is better, GPT-4o or gpt-oss-120b?
Across the 2 benchmarks both models have independently-run scores for, GPT-4o leads on 0 and gpt-oss-120b leads on 2. Benchmarks are one input — price and context window are on this page too.
Is GPT-4o cheaper than gpt-oss-120b?
gpt-oss-120b is cheaper: $0.070 versus $4.38 per million tokens blended at 3:1 input:output. Input alone: $2.50 vs $0.037. Output alone: $10.00 vs $0.170.
What context windows do GPT-4o and gpt-oss-120b have?
GPT-4o: 128,000 tokens. gpt-oss-120b: 131,072 tokens.
Who makes GPT-4o and gpt-oss-120b?
GPT-4o is made by OpenAI. gpt-oss-120b is made by OpenAI.