Gemini 3.5 Flash vs GPT-5.4 Mini
Head to head on 24 shared benchmarks, with price, context window, and release dates.
Benchmark scores
35evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash Google (Alphabet Inc.) | 64.7% | 71.8 | 57.9% | 39.0% | 92.2% | 42.7% | 76.3% | 78.9% | 78.2% | 64.9% | 75.6% | 84.6% | 88.2% | 82.0% | 68.1% | 31.0% | 49.9% | 53.1% | 74.4% | 40.9% | 53.1% | 62.9% | 48.7% | 95.3% | - | 26.0% | - | - | 1087elo | - | - | 76.3% | 55.8% | 76.6% | - | 64.3% |
| GPT-5.4 Mini OpenAI | 60.9% | 73 | 45.4% | 28.3% | 87.5% | 28.1% | 73.3% | 70.9% | 71.6% | 70.9% | 60.3% | 71.5% | 78.6% | 72.5% | 63.5% | 21.0% | 50.8% | 49.9% | 71.2% | 52.3% | 39.6% | 54.2% | 48.0% | 83.3% | 37.0% | - | 21.2% | 3.9% | - | 1662elo | 80.3% | - | - | - | 61.7 | 55.4% |
2 / 2 models
| Attribute | Gemini 3.5 Flash Google (Alphabet Inc.) | GPT-5.4 Mini OpenAI |
|---|---|---|
| Description | Gemini 3.5 Flash is an AI model from Google (Alphabet Inc.). | GPT-5.4 mini is an AI model from OpenAI. |
| Family | Gemini | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 19 May 2026 | 17 Mar 2026 |
| Context | 1,048,576 | 400,000 |
| Input $/1M | $1.50 | $0.75 |
| Output $/1M | $9.00 | $4.50 |
| Cache read $/1M | $0.150 | $0.075 |
| 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 | file, image, text |
| 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-5.4 Mini better?
- Across the 24 benchmarks both models report on Sophon, Gemini 3.5 Flash leads on 20 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-5.4 Mini compare on GPQA Diamond?
- Gemini 3.5 Flash scores 92.2% and GPT-5.4 Mini scores 87.5% on GPQA Diamond.
- Which is cheaper, Gemini 3.5 Flash or GPT-5.4 Mini?
- GPT-5.4 Mini is cheaper at $4.50 per million output tokens against $9.00 for Gemini 3.5 Flash - about 2.0x.
- When were Gemini 3.5 Flash and GPT-5.4 Mini released?
- Gemini 3.5 Flash was released 19 May 2026 by Google (Alphabet Inc.). GPT-5.4 Mini was released 17 Mar 2026 by OpenAI.
Comparing something else? Build your own side-by-side.