Claude Opus 4.5 vs gpt-oss-120b
Head to head on 21 shared benchmarks, with price, context window, and release dates.
Benchmark scores
51evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.5 Anthropic | 62.7% | 61.3% | 1683elo | 73.1 | 81.0% | 13.2% | 43.0% | 78.1% | 79.7% | 74.4% | 62.5% | 81.3% | 90.4% | 80.1% | 73.8% | 88.9% | 47.0% | 79.2% | 74.3% | 40.9% | 86.3% | - | - | - | 16.7% | - | 35.6% | 6.1% | 20.7% | 84.7% | 12.13 | - | 83.8% | 83.5% | - | - | 45.2% | 83.2% | - | 68.7% | 100.0% | 37.4 | 36.0% | 77.5% | 45.0% | 45.3 | - | 70.7% | 61.8 | - | 20.6% | 62.2% |
| gpt-oss-120b OpenAI | 66.7% | 58.2% | 959elo | 35.8 | 67.2% | 5.9% | 58.3% | 51.0% | 60.2% | 38.8% | 50.3% | 48.6% | 68.9% | 39.2% | 70.7% | 77.5% | 36.0% | 26.0% | 71.6% | 5.3% | 45.0% | 41.8% | 38.9% | 7.6% | - | 13.0% | - | - | - | - | - | 57.6 | - | - | 1.62 | 1.53 | - | - | 80.0% | - | - | - | - | - | - | - | 97.9% | - | - | 65.6% | - | 49.6% |
2 / 2 models
| Attribute | Claude Opus 4.5 Anthropic | gpt-oss-120b OpenAI |
|---|---|---|
| Description | Claude Opus 4.5 is an AI model from Anthropic. | GPT-Oss 120b is an AI model from OpenAI, released with open weights. |
| Family | Claude | GPT |
| Params | - | - |
| Open weights | closed | open |
| License | proprietary | apache-2.0 |
| Released | 24 Nov 2025 | 5 Aug 2025 |
| Context | 200,000 | 131,072 |
| Input $/1M | $5.00 | $0.15 |
| Output $/1M | $25.00 | $0.60 |
| Cache read $/1M | $0.500 | $0.030 |
| Cache write $/1M | $6.250 | - |
| Speed | 0 tok/s | 186 tok/s |
| Latency | 0.00 s | 0.50 s |
| Modalities | file, image, text | text |
| Providers | - | - |
| Publisher | Anthropic | OpenAI |
| Reported scores | GPQA Diamond67.2% (AA) Humanity's Last Exam (HLE)5.9% (AA) LiveCodeBench70.7% (AA) MMLU-Pro77.5% (AA) SciCode36.0% (AA) |
FAQ
- Is Claude Opus 4.5 or gpt-oss-120b better?
- Across the 21 benchmarks both models report on Sophon, Claude Opus 4.5 leads on 19 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Opus 4.5 and gpt-oss-120b compare on GPQA Diamond?
- Claude Opus 4.5 scores 81.0% and gpt-oss-120b scores 67.2% on GPQA Diamond.
- Which is cheaper, Claude Opus 4.5 or gpt-oss-120b?
- gpt-oss-120b is cheaper at $0.60 per million output tokens against $25.00 for Claude Opus 4.5 - about 41.7x.
- When were Claude Opus 4.5 and gpt-oss-120b released?
- Claude Opus 4.5 was released 24 Nov 2025 by Anthropic. gpt-oss-120b was released 5 Aug 2025 by OpenAI.
Comparing something else? Build your own side-by-side.