Claude Sonnet 4.6 vs GPT-4o
Head to head on 14 shared benchmarks, with price, context window, and release dates.
Benchmark scores
54evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 Anthropic | 65.3% | 32.4% | 79.7% | 11.2% | 42.4% | 78.4% | 80.0% | 63.9% | 77.7% | 67.7% | 44.1% | 77.1% | 42.4% | 78.9% | 87.1% | - | - | - | - | 47.2% | 47.6% | - | - | 1.35 | 78.0% | - | 1207elo | 1805elo | 79.9 | 51.0% | - | 92.2% | - | 76.1% | 86.5% | 86.4% | - | - | - | - | 89.3 | 72.1% | - | 45.0% | 46.6% | - | - | - | 76.3 | - | 50.6% | 60.6% | 51.5% | - | 62.8% |
| GPT-4o OpenAI | 45.9% | 0.3% | 54.3% | 2.4% | 34.3% | 55.1% | 46.1% | 70.1% | 49.0% | 57.4% | 33.3% | 74.5% | 8.3% | 25.1% | - | 18.2% | 15.0% | 6.0% | 38 | - | - | 0.0% | 0.33 | - | - | 6.1% | - | - | - | - | 96.1 | - | 0.0% | - | - | - | 30.9% | 75.9% | 10.8% | 74.8% | - | - | 54.0% | - | - | 5.71 | 21.6% | 61.2 | - | 0.98 | - | - | - | 32.5% | 33.4% |
2 / 2 models
| Attribute | Claude Sonnet 4.6 Anthropic | GPT-4o OpenAI |
|---|---|---|
| Description | Claude Sonnet 4.6 is an AI model from Anthropic. | GPT-4o is an AI model from OpenAI. |
| Family | Claude | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 17 Feb 2026 | 20 Nov 2024 |
| Context | 1,000,000 | 128,000 |
| Input $/1M | $3.00 | $2.50 |
| Output $/1M | $15.00 | $10.00 |
| Cache read $/1M | $0.300 | $1.250 |
| Cache write $/1M | $3.750 | - |
| Speed | 45 tok/s | 0 tok/s |
| Latency | 1.12 s | 0.00 s |
| Modalities | text, image, file | text, image, file |
| Providers | - | - |
| Publisher | Anthropic | OpenAI |
| Reported scores | GPQA Diamond79.7% (AA) Humanity's Last Exam (HLE)11.2% (AA) IFBench42.4% (AA) SciCode44.1% (AA) τ²-bench (Tau²-bench)78.9% (AA) | Taubench61.2 pass^1 GSM8K96.1 Accuracy ScholarSearch5.71 Social Sciences & Humanities (%) MortgageTax57.4% AIME202438 pass@1 |
FAQ
- Is Claude Sonnet 4.6 or GPT-4o better?
- Across the 14 benchmarks both models report on Sophon, Claude Sonnet 4.6 leads on 13 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Sonnet 4.6 and GPT-4o compare on GPQA Diamond?
- Claude Sonnet 4.6 scores 79.7% and GPT-4o scores 54.3% on GPQA Diamond.
- Which is cheaper, Claude Sonnet 4.6 or GPT-4o?
- GPT-4o is cheaper at $10.00 per million output tokens against $15.00 for Claude Sonnet 4.6 - about 1.5x.
- When were Claude Sonnet 4.6 and GPT-4o released?
- Claude Sonnet 4.6 was released 17 Feb 2026 by Anthropic. GPT-4o was released 20 Nov 2024 by OpenAI.
Comparing something else? Build your own side-by-side.