Claude Opus 4.6 vs gpt-oss-120b
Head to head on 19 shared benchmarks, with price, context window, and release dates.
Benchmark scores
51evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.6 Anthropic | 67.0% | 71.0% | 1804elo | 77.7 | 84.0% | 19.1% | 44.6% | 78.8% | 78.2% | 69.9% | 63.3% | 83.3% | 89.3% | 88.7% | 45.7% | 75.6% | 76.0% | 48.5% | 84.8% | - | - | 99.79 | 56.1% | 1.5 | - | - | 2.08 | 1223elo | 40.7% | - | 84.9% | 88771 | 58 | - | - | - | 78.5% | 48.2% | 86.7% | - | - | 68.5% | 93 | 50.0% | 51.6% | 44.5 | - | 72.0% | - | 80.6 | 57.6% | 66.5% |
| gpt-oss-120b OpenAI | 58.2% | 13.0% | 959elo | 35.8 | 67.2% | 5.9% | 58.3% | 51.0% | 60.2% | 38.8% | 50.3% | 48.6% | 68.9% | 39.2% | 36.0% | 26.0% | 71.6% | 5.3% | 45.0% | 41.8% | 66.7% | - | - | - | 38.9% | 7.6% | - | - | - | 57.6 | - | - | - | 70.7% | 1.62 | 1.53 | - | - | - | 80.0% | 77.5% | - | - | - | - | - | 97.9% | - | 65.6% | - | - | 49.6% |
2 / 2 models
| Attribute | Claude Opus 4.6 Anthropic | gpt-oss-120b OpenAI |
|---|---|---|
| Description | Claude Opus 4.6 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 | 5 Feb 2026 | 5 Aug 2025 |
| Context | 1,000,000 | 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 | text, image, file | text |
| Providers | - | - |
| Publisher | Anthropic | OpenAI |
| Reported scores | GPQA Diamond84.0% (AA) Humanity's Last Exam (HLE)19.1% (AA) SciCode45.7% (AA) τ²-bench (Tau²-bench)84.8% (AA) Terminal-Bench (Hard)48.5% (AA) | 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 4.6 or gpt-oss-120b better?
- Across the 19 benchmarks both models report on Sophon, Claude Opus 4.6 leads on 18 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Opus 4.6 and gpt-oss-120b compare on GPQA Diamond?
- Claude Opus 4.6 scores 84.0% and gpt-oss-120b scores 67.2% on GPQA Diamond.
- Which is cheaper, Claude Opus 4.6 or gpt-oss-120b?
- gpt-oss-120b is cheaper at $0.60 per million output tokens against $25.00 for Claude Opus 4.6 - about 41.7x.
- When were Claude Opus 4.6 and gpt-oss-120b released?
- Claude Opus 4.6 was released 5 Feb 2026 by Anthropic. gpt-oss-120b was released 5 Aug 2025 by OpenAI.
Comparing something else? Build your own side-by-side.