GPT-4.1 vs GPT-5
Head to head on 28 shared benchmarks, with price, context window, and release dates.
Benchmark scores
72evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 OpenAI | 88.0% | 94.6% | 94.3% | 0.15 | 61.1% | 57.7% | 1627elo | 32.4% | 83.3% | 85.4% | 28.5% | 73.1% | 84.6% | 0.52 | 1.62 | 99.4% | 92.7% | 92.7% | 87.1% | 0.0% | 65.5% | 42.9% | 74.4% | 73.4% | 32.6% | 90.0% | 90.0% | 84.8% | 46.7% | - | 91.1% | - | 0.0% | - | 0.0% | 68.1% | 4.58 | - | - | 80.0% | 80.0% | 72.8 | 91.7% | 0.0% | 88.9% | 100.0% | 48.9% | 83.4% | 58.2% | 37.5% | - | 100.0% | 0.0% | 49.6% | - | 83.7% | 93.3% | 10.0% | 60.0% | 0.26 | 0.0% | 18.0% | 43.7% | - | 74.9% | - | - | 2.34 | 87.5% | 0.86 | 20.1% | 54.8% | 61.9% |
| GPT-4.1 OpenAI | 52.4% | 43.7% | 34.7% | 1.64 | 63.1% | 12.4% | 1420elo | 5.5% | 60.9% | 66.6% | 4.2% | 43.0% | 45.7% | 0.49 | 0.49 | 91.3% | 32.1% | 32.1% | 80.6% | 50.5% | 65.9% | 38.1% | 39.6% | 75.1% | 13.6% | 92.0% | 92.0% | 47.1% | - | 0.0% | - | 26.7% | - | 61.5% | - | - | - | 83.7% | 1.55 | - | - | - | - | - | - | - | - | - | - | - | 70.8% | - | - | - | 69.4% | - | - | - | - | - | - | - | - | 8.57 | - | 31.1% | 10.0% | - | - | - | - | - | 48.0% |
2 / 2 models
| Attribute | GPT-4.1 OpenAI | GPT-5 OpenAI |
|---|---|---|
| Description | GPT-4.1 is an AI model from OpenAI. | OpenAI's August 2025 unified frontier model that auto-routes between a fast model and a deeper "thinking" variant. |
| Family | GPT | GPT 5 |
| Params | - | Undisclosed (closed) |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 14 Apr 2025 | 7 Aug 2025 |
| Context | 1,047,576 | 400,000 |
| Input $/1M | $2.00 | $1.25 |
| Output $/1M | $8.00 | $10.00 |
| Cache read $/1M | $0.500 | $0.125 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | image, text, file | text, image, file |
| Providers | - | openai |
| Publisher | OpenAI | OpenAI |
| Reported scores | ScholarSearch8.57 Social Sciences & Humanities (%) GPQA Diamond66.6% (AA) Humanity's Last Exam (HLE)4.2% (AA) IFBench43.0% (AA) | SWE-bench74.9% (Verified) GPQA Diamond85.4% (AA) Humanity's Last Exam (HLE)28.5% (AA) IFBench73.1% (AA) |
FAQ
- Is GPT-4.1 or GPT-5 better?
- Across the 28 benchmarks both models report on Sophon, GPT-5 leads on 21 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-4.1 and GPT-5 compare on GPQA Diamond?
- GPT-4.1 scores 66.6% and GPT-5 scores 85.4% on GPQA Diamond.
- Which is cheaper, GPT-4.1 or GPT-5?
- GPT-4.1 is cheaper at $8.00 per million output tokens against $10.00 for GPT-5 - about 1.3x.
- When were GPT-4.1 and GPT-5 released?
- GPT-4.1 was released 14 Apr 2025 by OpenAI. GPT-5 was released 7 Aug 2025 by OpenAI.
Other head-to-heads
56GPT-4.1 Mini vs GPT-541 shared evalsGPT-5 vs GPT-5 Mini36 shared evalsClaude Sonnet 4.5 vs GPT-531 shared evalsGPT-4.1 vs GPT-4.1 Mini28 shared evalsGPT-5 vs GPT-5 Nano28 shared evalsClaude 4 Sonnet vs GPT-525 shared evalsGemini 2.5 Pro vs GPT-524 shared evalsGPT-5 vs GPT-5.223 shared evalsClaude Opus 4.5 vs GPT-523 shared evalsGPT-4.1 vs GPT-5 Mini22 shared evalsGPT-4.1 vs GPT-4.1 Nano22 shared evalsGPT-4.1 Nano vs GPT-521 shared evalsGPT-5 vs Grok 4.1 Fast20 shared evalsGPT-4.1 vs GPT-5 Nano20 shared evalsClaude Sonnet 4.5 vs GPT-4.119 shared evalsGemini 3.1 Pro Preview vs GPT-519 shared evalsClaude Opus 4.6 vs GPT-519 shared evalsGPT-5 vs GPT-5.419 shared evalsDeepSeek V3.2 vs GPT-519 shared evalsGPT-4o vs GPT-519 shared evalsClaude 4 Sonnet vs GPT-4.119 shared evalsGemini 2.5 Pro vs GPT-4.119 shared evalsGPT-4.1 vs GPT-4o19 shared evalsGPT-5 vs GPT-5.518 shared evalsGPT-5 vs Kimi K2.518 shared evalsClaude Opus 4.8 vs GPT-517 shared evalsClaude Opus 4.7 vs GPT-517 shared evalsGPT-5 vs gpt-oss-120b17 shared evalsGLM 4.7 vs GPT-517 shared evalsClaude Fable 5 vs GPT-516 shared evalsGPT-4o-mini vs GPT-516 shared evalsClaude Sonnet 4.6 vs GPT-516 shared evalsGLM 5.1 vs GPT-516 shared evalsGPT-5 vs GPT-5.4 Mini16 shared evalsClaude Opus 4.5 vs GPT-4.116 shared evalsGPT-4.1 vs GPT-4o-mini16 shared evalsGPT-4.1 vs gpt-oss-120b16 shared evalsGPT-5 vs Qwen3.6 Plus15 shared evalsGPT-4.1 vs GPT-5.215 shared evalsDeepSeek V3.2 vs GPT-4.115 shared evalsGemini 3.1 Pro Preview vs GPT-4.113 shared evalsClaude Opus 4.6 vs GPT-4.113 shared evalsGPT-4.1 vs GPT-5.413 shared evalsGPT-4.1 vs Grok 4.1 Fast13 shared evalsGLM 4.7 vs GPT-4.113 shared evalsGPT-5 vs GPT-6 Astra12 shared evalsGPT-4.1 vs GPT-5.512 shared evalsGPT-4.1 vs Kimi K2.512 shared evalsClaude Sonnet 4.6 vs GPT-4.112 shared evalsClaude Opus 4.8 vs GPT-4.111 shared evalsGLM 5.1 vs GPT-4.111 shared evalsClaude Opus 4.7 vs GPT-4.111 shared evalsGPT-4.1 vs GPT-5.4 Mini11 shared evalsClaude Fable 5 vs GPT-4.110 shared evalsGPT-4.1 vs Qwen3.6 Plus10 shared evalsGPT-4.1 vs GPT-6 Astra5 shared evals
Comparing something else? Build your own side-by-side.