GPT-4o-mini vs GPT-5
Head to head on 16 shared benchmarks, with price, context window, and release dates.
Benchmark scores
82evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 OpenAI | 88.0% | 94.6% | 94.3% | 61.1% | 1627elo | 85.4% | 28.5% | 73.1% | 58.2% | 84.6% | 99.4% | 87.1% | 65.5% | 42.9% | 73.4% | 0.86 | 46.7% | - | 91.1% | - | 0.0% | 0.15 | 0.0% | 68.1% | 4.58 | - | - | 57.7% | - | 80.0% | 80.0% | 72.8 | 91.7% | 32.4% | 0.0% | 88.9% | 83.3% | 100.0% | - | - | - | 48.9% | 83.4% | - | - | - | - | 37.5% | 0.52 | 1.62 | 100.0% | 0.0% | 92.7% | 92.7% | 49.6% | - | 83.7% | 93.3% | 10.0% | 0.0% | - | 60.0% | 0.26 | 0.0% | 18.0% | 43.7% | - | 74.9% | 74.4% | - | 2.34 | 32.6% | 87.5% | 20.1% | - | - | 54.8% | - | 90.0% | 90.0% | - | 84.8% | 61.9% |
| GPT-4o-mini OpenAI | 3.6% | 11.7% | 14.7% | 45.5% | 873elo | 42.6% | 4.2% | 31.0% | 72.0% | 23.4% | 78.9% | 64.8% | 54.5% | 22.9% | 60.5% | 0.36 | - | 16.7% | - | 50.7% | - | - | - | - | - | 0.29 | 0.0% | - | 0.0% | - | - | - | - | - | - | - | - | - | 0.0% | 1.54 | 0.0% | - | - | 47.2% | 43.0% | 65.8% | 32.9% | - | - | - | - | - | - | - | - | 62.8% | - | - | - | - | 78.0% | - | - | - | - | - | 3.81 | - | - | 100.0% | - | - | - | - | 0.78 | 83.3% | - | 54.5% | - | - | 22.5% | - | 39.6% |
2 / 2 models
| Attribute | GPT-4o-mini OpenAI | GPT-5 OpenAI |
|---|---|---|
| Description | GPT-4o Mini 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 | 18 Jul 2024 | 7 Aug 2025 |
| Context | 128,000 | 400,000 |
| Input $/1M | $0.15 | $1.25 |
| Output $/1M | $0.60 | $10.00 |
| Cache read $/1M | $0.075 | $0.125 |
| 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 | - | openai |
| Publisher | OpenAI | OpenAI |
| Reported scores | SWE-bench74.9% (Verified) GPQA Diamond85.4% (AA) Humanity's Last Exam (HLE)28.5% (AA) IFBench73.1% (AA) |
FAQ
- Is GPT-4o-mini or GPT-5 better?
- Across the 16 benchmarks both models report on Sophon, GPT-5 leads on 15 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-4o-mini and GPT-5 compare on GPQA Diamond?
- GPT-4o-mini scores 42.6% and GPT-5 scores 85.4% on GPQA Diamond.
- Which is cheaper, GPT-4o-mini or GPT-5?
- GPT-4o-mini is cheaper at $0.60 per million output tokens against $10.00 for GPT-5 - about 16.7x.
- When were GPT-4o-mini and GPT-5 released?
- GPT-4o-mini was released 18 Jul 2024 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-5 vs GPT-5 Nano28 shared evalsGPT-4.1 vs GPT-528 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 Mini vs GPT-4o-mini22 shared evalsGPT-4.1 Nano vs GPT-521 shared evalsGPT-4o vs GPT-4o-mini21 shared evalsGPT-5 vs Grok 4.1 Fast20 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 evalsGemini 2.5 Pro vs GPT-4o-mini19 shared evalsGPT-4o-mini vs GPT-5 Mini18 shared evalsGPT-5 vs GPT-5.518 shared evalsGPT-5 vs Kimi K2.518 shared evalsClaude 4 Sonnet vs GPT-4o-mini18 shared evalsClaude Sonnet 4.5 vs GPT-4o-mini17 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 evalsGPT-4.1 Nano vs GPT-4o-mini17 shared evalsClaude Fable 5 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 evalsGPT-4o-mini vs GPT-5 Nano16 shared evalsGPT-4.1 vs GPT-4o-mini16 shared evalsGPT-5 vs Qwen3.6 Plus15 shared evalsGPT-4o-mini vs GPT-5.215 shared evalsClaude Opus 4.5 vs GPT-4o-mini15 shared evalsDeepSeek V3.2 vs GPT-4o-mini15 shared evalsGPT-4o-mini vs Grok 4.1 Fast15 shared evalsGPT-4o-mini vs gpt-oss-120b15 shared evalsGLM 4.7 vs GPT-4o-mini14 shared evalsGPT-4o-mini vs GPT-5.513 shared evalsGPT-5 vs GPT-6 Astra12 shared evalsGemini 3.1 Pro Preview vs GPT-4o-mini12 shared evalsClaude Opus 4.8 vs GPT-4o-mini12 shared evalsClaude Fable 5 vs GPT-4o-mini12 shared evalsClaude Opus 4.6 vs GPT-4o-mini12 shared evalsGPT-4o-mini vs GPT-5.412 shared evalsGPT-4o-mini vs Kimi K2.512 shared evalsClaude Sonnet 4.6 vs GPT-4o-mini12 shared evalsGLM 5.1 vs GPT-4o-mini12 shared evalsClaude Opus 4.7 vs GPT-4o-mini12 shared evalsGPT-4o-mini vs GPT-5.4 Mini12 shared evalsGPT-4o-mini vs Qwen3.6 Plus11 shared evalsGPT-4o-mini vs GPT-6 Astra4 shared evals
Comparing something else? Build your own side-by-side.