Gemini 3.5 Flash vs GPT-5 Mini
Head to head on 23 shared benchmarks, with price, context window, and release dates.
Benchmark scores
71evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash Google (Alphabet Inc.) | 64.7% | 71.8 | 39.0% | 92.2% | 42.7% | 76.3% | 78.9% | 78.2% | 64.9% | 75.6% | 84.6% | 88.2% | 82.0% | 55.8% | 76.6% | 68.1% | 31.0% | 49.9% | 53.1% | 74.4% | 40.9% | 48.7% | 95.3% | - | - | - | - | - | - | - | - | - | - | 26.0% | - | - | - | - | - | 1087elo | - | - | 57.9% | - | - | - | - | - | - | - | - | - | - | 76.3% | - | - | - | - | - | - | - | - | - | - | - | 53.1% | 62.9% | - | - | - | - | 64.3% |
| GPT-5 Mini OpenAI | 60.2% | 56.2 | 27.2% | 82.8% | 21.5% | 75.4% | 69.1% | 68.2% | 55.2% | 65.3% | 75.5% | 82.2% | 68.3% | 43.0% | 80.6% | 66.9% | 9.0% | 43.0% | 39.2% | 75.2% | 33.3% | 14.2% | 68.4% | 0.0% | 90.7% | 0.0% | 1.13 | 0.0% | -0.15 | 20.0% | 25.0% | 40.0% | 1.7 | - | 100.0% | 18.1% | 2.8% | 100.0% | 66.7% | - | 1310elo | 0.0% | - | 88.3% | 60.0% | 100.0% | 90.0% | 47.2% | 80.0% | 83.8% | 0.0% | 1.54 | 1.54 | - | 80.0% | 83.7% | 16.8% | 4.95 | 39.7% | 59.8% | 0.0% | 9.5% | 0.0% | 86.1% | 0.49 | - | - | 39.21 | 272.11 | 86.0% | 86.0% | 51.6% |
2 / 2 models
| Attribute | Gemini 3.5 Flash Google (Alphabet Inc.) | GPT-5 Mini OpenAI |
|---|---|---|
| Description | Gemini 3.5 Flash is an AI model from Google (Alphabet Inc.). | GPT-5 mini is an AI model from OpenAI. |
| Family | Gemini | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 19 May 2026 | 7 Aug 2025 |
| Context | 1,048,576 | 400,000 |
| Input $/1M | $1.50 | $0.25 |
| Output $/1M | $9.00 | $2.00 |
| Cache read $/1M | $0.150 | $0.025 |
| Cache write $/1M | $0.083 | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image, video, file, audio | text, image, file |
| Providers | - | - |
| Publisher | Google (Alphabet Inc.) | OpenAI |
| Reported scores | Humanity's Last Exam (HLE)42.7% (AA) τ²-bench (Tau²-bench)95.3% (AA) Terminal-Bench (Hard)40.9% (AA) Vals Index53.1% |
FAQ
- Is Gemini 3.5 Flash or GPT-5 Mini better?
- Across the 23 benchmarks both models report on Sophon, Gemini 3.5 Flash leads on 21 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Gemini 3.5 Flash and GPT-5 Mini compare on GPQA Diamond?
- Gemini 3.5 Flash scores 92.2% and GPT-5 Mini scores 82.8% on GPQA Diamond.
- Which is cheaper, Gemini 3.5 Flash or GPT-5 Mini?
- GPT-5 Mini is cheaper at $2.00 per million output tokens against $9.00 for Gemini 3.5 Flash - about 4.5x.
- When were Gemini 3.5 Flash and GPT-5 Mini released?
- Gemini 3.5 Flash was released 19 May 2026 by Google (Alphabet Inc.). GPT-5 Mini was released 7 Aug 2025 by OpenAI.
Comparing something else? Build your own side-by-side.