All Comparisons
Gemini 2.5 Pro vs GPT-4.1
Gemini 2.5 Pro
Google 🇺🇸
53.5
#169—
medium$1.25/M in · $10.00/M out
1.0M context
GPT-4.1
OpenAI 🇺🇸
32.5
#256—
high$2.00/M in · $8.00/M out
1.0M context
Most Affordable
Gemini 2.5 Pro
$1.25/M input
Largest Context
Gemini 2.5 Pro
1.0M tokens
Best Benchmark Score
Gemini 2.5 Pro
53.5/100
Model Specifications
| Spec | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| Provider | OpenAI | |
| Release Date | May 2025 | Apr 2025 |
| Knowledge Cutoff | 2025-01-31 | 2024-06-30 |
| Parameters | Undisclosed | Undisclosed |
| Context Window | 1.0M | 1.0M |
| Max Output | 65.5K | 32.8K |
| Open Source | No | No |
| License | proprietary | proprietary |
| Tokenizer | Gemini | GPT |
| Modality | text+image+file+audio+video->text | text+image+file->text |
| Reasoning Model | No | No |
| Moderated | No | Yes |
| Expiration Date | Oct 20, 2026 | None |
Pricing Comparison
| Price (per 1M tokens) | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| Input | $1.25 | $2.00 |
| Output | $10.00 | $8.00 |
| Image | $1.25 | — |
| Cache Read | $0.13 | $0.50 |
| Cache Write | $0.38 | — |
| Reasoning | $10.00 | — |
| Audio | $1.25 | — |
API Provider Pricing
Capabilities
| Feature | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| Text Input | ||
| Image Input (Vision) | ||
| Audio Input | ||
| Video Input | ||
| File Input | ||
| Image Output | ||
| Audio Output | ||
| Tool Use | ||
| Structured Output (JSON) | ||
| Streaming | ||
| Reasoning Tokens | ||
| Web Search | ||
| Temperature Control | ||
| Top-P Sampling | ||
| Stop Sequences | ||
| Seed (Reproducibility) | ||
| Log Probabilities |
Category Comparison
Benchmark-by-Benchmark
coding
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 63.2 | 54.6 |
math
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| AIME 2025 | 83 | 46.4 |
reasoning
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 83 | 66.3 |
| Humanity's Last Exam | 17.8 | 5.4 |
| ARC-AGI v2 | 4.9 | — |
multimodal
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| MMMU | 79.6 | 74.8 |
| CharXiv Reasoning | — | 56.7 |
agent
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| TAU-Bench Retail | — | 68 |
Category Winners
coding
44.0
math
57.2
reasoning
35.6
general
69.1
multimodal
79.3
agent
50.7