GPT-4o vs GPT-5 Mini
Head to head on 20 shared benchmarks, with price, context window, and release dates.
Benchmark scores
78evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 Mini OpenAI | 0.0% | 90.7% | 60.2% | 100.0% | 27.2% | 82.8% | 21.5% | 75.4% | 69.1% | 68.2% | 65.3% | 75.5% | 83.8% | 83.7% | 66.9% | 39.0% | 59.8% | 75.2% | 33.3% | 68.4% | - | - | 0.0% | 1.13 | 0.0% | - | -0.15 | 20.0% | 25.0% | - | 40.0% | 1.7 | 100.0% | 18.1% | 2.8% | 66.7% | 1313elo | 56.2 | 0.0% | 88.3% | 60.0% | 100.0% | - | 90.0% | 47.2% | 80.0% | - | 55.2% | 82.2% | 68.3% | 0.0% | 1.54 | 1.54 | - | 43.0% | - | 80.6% | 80.0% | - | 9.0% | 43.0% | - | 16.8% | 4.95 | 39.7% | - | 0.0% | 9.5% | 0.0% | - | 86.1% | 0.49 | 39.21 | 272.11 | 14.2% | 86.0% | 86.0% | - | 51.6% |
| GPT-4o OpenAI | 18.2% | 6.0% | 45.9% | 6.1% | 0.3% | 54.3% | 2.4% | 34.3% | 55.1% | 46.1% | 70.1% | 49.0% | 30.9% | 74.8% | 57.4% | 33.3% | 21.6% | 74.5% | 8.3% | 25.1% | 15.0% | 38 | - | - | - | 0.0% | - | - | - | 0.33 | - | - | - | - | - | - | - | - | - | - | - | - | 96.1 | - | - | - | 0.0% | - | - | - | - | - | - | 75.9% | - | 10.8% | - | - | 54.0% | - | - | 5.71 | - | - | - | 61.2 | - | - | - | 0.98 | - | - | - | - | - | - | - | 32.5% | 33.4% |
2 / 2 models
| Attribute | GPT-4o OpenAI | GPT-5 Mini OpenAI |
|---|---|---|
| Description | GPT-4o is an AI model from OpenAI. | GPT-5 mini is an AI model from OpenAI. |
| Family | GPT | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 20 Nov 2024 | 7 Aug 2025 |
| Context | 128,000 | 400,000 |
| Input $/1M | $2.50 | $0.25 |
| Output $/1M | $10.00 | $2.00 |
| Cache read $/1M | $1.250 | $0.025 |
| 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 |
FAQ
- Is GPT-4o or GPT-5 Mini better?
- Across the 20 benchmarks both models report on Sophon, GPT-5 Mini leads on 18 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-4o and GPT-5 Mini compare on GPQA Diamond?
- GPT-4o scores 54.3% and GPT-5 Mini scores 82.8% on GPQA Diamond.
- Which is cheaper, GPT-4o or GPT-5 Mini?
- GPT-5 Mini is cheaper at $2.00 per million output tokens against $10.00 for GPT-4o - about 5.0x.
- When were GPT-4o and GPT-5 Mini released?
- GPT-4o was released 20 Nov 2024 by OpenAI. GPT-5 Mini was released 7 Aug 2025 by OpenAI.
Other head-to-heads
56GPT-5 Mini vs GPT-5 Nano38 shared evalsGPT-5 vs GPT-5 Mini36 shared evalsGPT-4.1 Mini vs GPT-5 Mini32 shared evalsGPT-5 Mini vs GPT-5.232 shared evalsClaude Sonnet 4.5 vs GPT-5 Mini31 shared evalsClaude Opus 4.5 vs GPT-5 Mini31 shared evalsClaude 4 Sonnet vs GPT-5 Mini29 shared evalsClaude Opus 4.6 vs GPT-5 Mini28 shared evalsGemini 3.1 Pro Preview vs GPT-5 Mini27 shared evalsGPT-5 Mini vs GPT-5.427 shared evalsDeepSeek V3.2 vs GPT-5 Mini26 shared evalsGemini 2.5 Pro vs GPT-5 Mini26 shared evalsGPT-5 Mini vs Grok 4.1 Fast26 shared evalsGPT-5 Mini vs GPT-5.525 shared evalsGPT-5 Mini vs Kimi K2.525 shared evalsGLM 5.1 vs GPT-5 Mini25 shared evalsClaude Opus 4.7 vs GPT-5 Mini25 shared evalsGPT-5 Mini vs gpt-oss-120b25 shared evalsGLM 4.7 vs GPT-5 Mini25 shared evalsClaude Opus 4.8 vs GPT-5 Mini24 shared evalsGPT-5.4 Mini vs GPT-5 Mini24 shared evalsClaude Fable 5 vs GPT-5 Mini23 shared evalsClaude Sonnet 4.6 vs GPT-5 Mini23 shared evalsGPT-4.1 vs GPT-5 Mini22 shared evalsGemini 2.5 Pro vs GPT-4o22 shared evalsClaude Sonnet 4.5 vs GPT-4o21 shared evalsGPT-4.1 Nano vs GPT-5 Mini21 shared evalsGPT-5 Mini vs Qwen3.6 Plus21 shared evalsGPT-4o vs GPT-4o-mini21 shared evalsGPT-4.1 Mini vs GPT-4o20 shared evalsClaude 4 Sonnet vs GPT-4o20 shared evalsGPT-4o vs GPT-519 shared evalsGPT-4.1 vs GPT-4o19 shared evalsGPT-4o-mini vs GPT-5 Mini18 shared evalsGPT-4o vs GPT-5 Nano18 shared evalsGPT-4o vs GPT-5.218 shared evalsClaude Opus 4.5 vs GPT-4o18 shared evalsDeepSeek V3.2 vs GPT-4o18 shared evalsGPT-4o vs gpt-oss-120b17 shared evalsGPT-4.1 Nano vs GPT-4o16 shared evalsGPT-4o vs Grok 4.1 Fast16 shared evalsGLM 4.7 vs GPT-4o16 shared evalsGPT-4o vs GPT-5.515 shared evalsClaude Opus 4.6 vs GPT-4o15 shared evalsGPT-4o vs Kimi K2.515 shared evalsGemini 3.1 Pro Preview vs GPT-4o14 shared evalsClaude Opus 4.8 vs GPT-4o14 shared evalsGPT-4o vs GPT-5.414 shared evalsClaude Sonnet 4.6 vs GPT-4o14 shared evalsGLM 5.1 vs GPT-4o14 shared evalsClaude Opus 4.7 vs GPT-4o14 shared evalsGPT-4o vs Qwen3.6 Plus14 shared evalsGPT-4o vs GPT-5.4 Mini14 shared evalsClaude Fable 5 vs GPT-4o13 shared evalsGPT-5 Mini vs GPT-6 Astra12 shared evalsGPT-4o vs GPT-6 Astra4 shared evals
Comparing something else? Build your own side-by-side.