Key Takeaways
Gemini 2.5 Flash wins:
- Larger context window
- Supports vision
- Has reasoning mode
- Supports tool calls
GPT-OSS-120b wins:
- Cheaper input tokens
- Cheaper output tokens
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
Price Advantage
GPT-OSS-120b
Benchmark Advantage
GPT-OSS-120b
Context Window
Gemini 2.5 Flash
Speed
GPT-OSS-120b
Pricing Comparison
Price Comparison
| Metric | Gemini 2.5 Flash | GPT-OSS-120b | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.30 | $0.04 | GPT-OSS-120b |
| Output (per 1M tokens) | $2.50 | $0.19 | GPT-OSS-120b |
| Cache Read (per 1M) | $0.03 | N/A | Gemini 2.5 Flash |
| Cache Write (per 1M) | $0.08 | N/A | Gemini 2.5 Flash |
Using a 3:1 input/output ratio, GPT-OSS-120b is 91% cheaper overall.
Gemini 2.5 Flash Providers
Vercel $0.30 (Cheapest)
Google AI Studio $0.30 (Cheapest)
Google $0.30 (Cheapest)
GPT-OSS-120b Providers
Chutes $0.04 (Cheapest)
SiliconFlow $0.05
Novita $0.05
NCompass $0.05
Clarifai $0.09
Benchmark Comparison
8
Benchmarks Compared
1
Gemini 2.5 Flash Wins
5
GPT-OSS-120b Wins
Benchmark Scores
| Benchmark | Gemini 2.5 Flash | GPT-OSS-120b | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 21.1 | 33.3 | |
Coding Index Code generation & understanding | 17.8 | 28.6 | |
Math Index Mathematical reasoning | 60.3 | 93.4 | |
MMLU Pro Academic knowledge | 80.9 | 80.8 | - |
GPQA Graduate-level science | 68.3 | 78.2 | |
LiveCodeBench Competitive programming | 49.5 | 87.8 | |
Aider Real-world code editing | 55.1 | 41.8 | |
AIME Competition math | 50.0 | - | - |
GPT-OSS-120b significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Gemini 2.5 Flash
Other models
Context & Performance
Context Window
Gemini 2.5 Flash
1,048,576
tokens
Max output: 65,535 tokens
GPT-OSS-120b
131,072
tokens
Gemini 2.5 Flash has a 88% larger context window.
Speed Performance
| Metric | Gemini 2.5 Flash | GPT-OSS-120b | Winner |
|---|---|---|---|
| Tokens/second | 246.2 tok/s | 301.3 tok/s | |
| Time to First Token | 0.47s | 0.51s |
GPT-OSS-120b responds 22% faster on average.
Capabilities
Feature Comparison
| Feature | Gemini 2.5 Flash | GPT-OSS-120b |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Gemini 2.5 Flash | GPT-OSS-120b |
|---|---|---|
| License | Proprietary | Open Source |
| Author | OpenAI | |
| Released | Jun 2025 | Aug 2025 |
Gemini 2.5 Flash Modalities
Input
fileimagetextaudiovideo
Output
text
GPT-OSS-120b Modalities
Input
text
Output
text