Key Takeaways
Claude Sonnet 4.5 wins:
- Larger context window
- Higher intelligence benchmark
- Better at coding
- Supports vision
- Has reasoning mode
- Supports tool calls
GPT-OSS-120b wins:
- Cheaper input tokens
- Cheaper output tokens
- Faster response time
- Better at math
Price Advantage
GPT-OSS-120b
Benchmark Advantage
Claude Sonnet 4.5
Context Window
Claude Sonnet 4.5
Speed
GPT-OSS-120b
Pricing Comparison
Price Comparison
| Metric | Claude Sonnet 4.5 | GPT-OSS-120b | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $3.00 | $0.04 | GPT-OSS-120b |
| Output (per 1M tokens) | $15.00 | $0.19 | GPT-OSS-120b |
| Cache Read (per 1M) | $0.30 | N/A | Claude Sonnet 4.5 |
| Cache Write (per 1M) | $3.75 | N/A | Claude Sonnet 4.5 |
Using a 3:1 input/output ratio, GPT-OSS-120b is 99% cheaper overall.
Claude Sonnet 4.5 Providers
Amazon Bedrock $3.00 (Cheapest)
Google $3.00 (Cheapest)
Anthropic $3.00 (Cheapest)
GPT-OSS-120b Providers
Chutes $0.04 (Cheapest)
SiliconFlow $0.05
Novita $0.05
NCompass $0.05
Clarifai $0.09
Benchmark Comparison
7
Benchmarks Compared
3
Claude Sonnet 4.5 Wins
3
GPT-OSS-120b Wins
Benchmark Scores
| Benchmark | Claude Sonnet 4.5 | GPT-OSS-120b | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 37.1 | 33.3 | |
Coding Index Code generation & understanding | 33.5 | 28.6 | |
Math Index Mathematical reasoning | 37.0 | 93.4 | |
MMLU Pro Academic knowledge | 86.0 | 80.8 | |
GPQA Graduate-level science | 72.7 | 78.2 | |
LiveCodeBench Competitive programming | 59.0 | 87.8 | |
Aider Real-world code editing | - | 41.8 | - |
GPT-OSS-120b shows stronger mathematical reasoning abilities.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Claude Sonnet 4.5
Other models
Context & Performance
Context Window
Claude Sonnet 4.5
1,000,000
tokens
Max output: 64,000 tokens
GPT-OSS-120b
131,072
tokens
Claude Sonnet 4.5 has a 87% larger context window.
Speed Performance
| Metric | Claude Sonnet 4.5 | GPT-OSS-120b | Winner |
|---|---|---|---|
| Tokens/second | 70.4 tok/s | 301.3 tok/s | |
| Time to First Token | 1.07s | 0.51s |
GPT-OSS-120b responds 328% faster on average.
Capabilities
Feature Comparison
| Feature | Claude Sonnet 4.5 | GPT-OSS-120b |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Claude Sonnet 4.5 | GPT-OSS-120b |
|---|---|---|
| License | Proprietary | Open Source |
| Author | Anthropic | OpenAI |
| Released | Sep 2025 | Aug 2025 |
Claude Sonnet 4.5 Modalities
Input
textimagefile
Output
text
GPT-OSS-120b Modalities
Input
text
Output
text