Best Benchmark Score
o3
47.9/100
Model Specifications
| Spec | Gemini 2.0 Flash | o3 |
|---|---|---|
| Provider | OpenAI | |
| Release Date | Dec 2024 | Apr 2025 |
| Knowledge Cutoff | 2024-08-01 | 2024-05-31 |
| Parameters | Undisclosed | Undisclosed |
| Context Window | — | — |
| Max Output | — | — |
| Open Source | No | No |
| License | proprietary | proprietary |
| Tokenizer | — | — |
| Modality | — | — |
| Reasoning Model | No | No |
| Moderated | No | No |
Pricing Comparison
| Price (per 1M tokens) | Gemini 2.0 Flash | o3 |
|---|
API Provider Pricing
Capabilities
| Feature | Gemini 2.0 Flash | o3 |
|---|---|---|
| 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
image_quality
| Benchmark | Gemini 2.0 Flash | o3 |
|---|---|---|
| Image Arena Elo | 1260 | — |
reasoning
| Benchmark | Gemini 2.0 Flash | o3 |
|---|---|---|
| GPQA Diamond | 62.1 | 83.3 |
| Humanity's Last Exam | — | 14.7 |
| ARC-AGI v2 | — | 6.5 |
multimodal
| Benchmark | Gemini 2.0 Flash | o3 |
|---|---|---|
| MMMU | 70.7 | 82.9 |
| MMMU-Pro | — | 76.4 |
| CharXiv Reasoning | — | 78.6 |
coding
| Benchmark | Gemini 2.0 Flash | o3 |
|---|---|---|
| SWE-bench Verified | — | 69.1 |
math
| Benchmark | Gemini 2.0 Flash | o3 |
|---|---|---|
| AIME 2025 | — | 86.4 |
| FrontierMath | — | 15.8 |
agent
| Benchmark | Gemini 2.0 Flash | o3 |
|---|---|---|
| BrowseComp | — | 49.7 |
Category Winners
coding
58.4
math
43.5
reasoning
39.5
multimodal
73.4
agent
23.4