Model comparison
gpt-oss-120b vs Claude Opus 4
- Input
- $0.039 / 1M tokens
- Output
- $0.18 / 1M tokens
- Context
- 131K
- Released
- 2025-08-05
- Input
- $15.00
- Output
- $75.00
- Context
- 200K
- Released
- 2025-05-22
Gpt-oss-120b scores higher on 3 of the 4 benchmarks both models report (the other leads on 1); gpt-oss-120b is cheaper on input tokens ($0 vs $15 per 1M, 384.6×); Claude Opus 4 has the larger context window (200K vs 131K); gpt-oss-120b ships open weights while Claude Opus 4 is API-only.
Specs and pricing side by side
| Spec | gpt-oss-120b | Claude Opus 4 |
|---|---|---|
| Maker | OpenAI | Anthropic |
| Released | 2025-08-05 | 2025-05-22 |
| Context window | 131K | 200K |
| Max output | 131K | 32K |
| Input price | $0.039 / 1M tokens | $15.00 |
| Output price | $0.18 / 1M tokens | $75.00 |
| Parameters | 116.8B total / 5.1B active (MoE) | |
| License | Apache 2.0 | Proprietary |
| Weights | Open weights | API only |
| Modalities | Text | Text, Vision |
| Knowledge cutoff | June 2024 | not published |
Benchmarks both models report
| Benchmark | gpt-oss-120b | Claude Opus 4 |
|---|---|---|
| MMLU | 90% | 87.4% |
| GPQA Diamond | 80.1% | 74.9% |
| AIME 2025 | 97.9% | 33.9% |
| SWE-bench Verified | 62.4% | 72.5% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick gpt-oss-120b if…
- You care about MMLU, GPQA Diamond, AIME 2025 (it scores higher on 3 shared benchmarks).
- Cost matters: input tokens cost 384.6× less ($0 vs $15 per 1M).
- You want to self-host or fine-tune (open weights, Apache 2.0).
- Your use case is: on-premise / private reasoning assistants where data cannot leave the org.
Pick Claude Opus 4 if…
- You care about SWE-bench Verified (it scores higher on 1 shared benchmark).
- You need the longer context (200K vs 131K).
- You need Vision input, which gpt-oss-120b lacks.
- Your use case is: autonomous and agentic coding workflows.
FAQ
Which is better, gpt-oss-120b or Claude Opus 4?
Gpt-oss-120b scores higher on 3 of the 4 benchmarks both models report (the other leads on 1); gpt-oss-120b is cheaper on input tokens ($0 vs $15 per 1M, 384.6×); Claude Opus 4 has the larger context window (200K vs 131K); gpt-oss-120b ships open weights while Claude Opus 4 is API-only. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is gpt-oss-120b?
gpt-oss-120b: $0.039 / 1M tokens input, $0.18 / 1M tokens output. Claude Opus 4: $15.00 input, $75.00 output (list API prices as published by each maker).
What are the context windows of gpt-oss-120b and Claude Opus 4?
gpt-oss-120b offers 131K with up to 131K output; Claude Opus 4 offers 200K with up to 32K output.
Is gpt-oss-120b newer than Claude Opus 4?
gpt-oss-120b was released 2025-08-05; Claude Opus 4 was released 2025-05-22.