GPT-4o vs GPT-5.4
Head to head on 14 shared benchmarks, with price, context window, and release dates.
Benchmark scores
58evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.4 OpenAI | 65.3% | 47.6% | 74.8% | 11.3% | 48.4% | 82.0% | 77.5% | 70.2% | 82.6% | 68.3% | 47.1% | 74.0% | 37.9% | 36.0% | - | - | - | - | 13.1% | - | - | 1.47 | 81.0% | 34.1% | 9.0% | - | 1272elo | 1836elo | 78.3 | 87.2% | - | 78.5% | 92063 | - | 79.3% | 94.1% | 88.1% | - | - | 82.8% | 41.3% | - | 77.5% | - | 86 | 52.2% | - | 56.0% | 43.3% | - | -0.61 | 40.8 | - | - | 80 | - | 67.4% | - | 60.3% |
| 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 | GPT-4o OpenAI | GPT-5.4 OpenAI |
|---|---|---|
| Description | GPT-4o is an AI model from OpenAI. | GPT-5.4 is an AI model from OpenAI. |
| Family | GPT | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 20 Nov 2024 | 5 Mar 2026 |
| Context | 128,000 | 1,050,000 |
| Input $/1M | $2.50 | $2.50 |
| Output $/1M | $10.00 | $15.00 |
| Cache read $/1M | $1.250 | $0.250 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image, file | text, image, file |
| Providers | - | - |
| Publisher | OpenAI | OpenAI |
| Reported scores | Taubench61.2 pass^1 GSM8K96.1 Accuracy ScholarSearch5.71 Social Sciences & Humanities (%) MortgageTax57.4% AIME202438 pass@1 | GPQA Diamond74.8% (AA) SciCode47.1% (AA) τ²-bench (Tau²-bench)36.0% (AA) Terminal-Bench (Hard)37.9% (AA) Vibe Code Bench v1.167.4% |
FAQ
- Is GPT-4o or GPT-5.4 better?
- Across the 14 benchmarks both models report on Sophon, GPT-5.4 leads on 13 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-4o and GPT-5.4 compare on GPQA Diamond?
- GPT-4o scores 54.3% and GPT-5.4 scores 74.8% on GPQA Diamond.
- Which is cheaper, GPT-4o or GPT-5.4?
- GPT-4o is cheaper at $10.00 per million output tokens against $15.00 for GPT-5.4 - about 1.5x.
- When were GPT-4o and GPT-5.4 released?
- GPT-4o was released 20 Nov 2024 by OpenAI. GPT-5.4 was released 5 Mar 2026 by OpenAI.
Comparing something else? Build your own side-by-side.