Model Comparison
GPT-3.5 Turbo (0613)
vs. gpt-oss-20B (high)
Comparing 2 AI models · 10 benchmarks · OpenAI
Recommended Pick
Op GPT-3.5 Turbo (0613) 4 metric wins Strongest on: Input price, Output price, TTFT
Lowest Price
GPT-3.5 Turbo (0613)
$0.00/1M input price
Best for Coding
gpt-oss-20B (high)
18.5 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Price gap
GPT-3.5 Turbo (0613) is ∞x cheaper on input tokens than gpt-oss-20B (high).
Top-pick rationale
GPT-3.5 Turbo (0613) wins 4 measurable categories, including Input price, Output price, TTFT, Latency.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
GPT-3.5 Turbo (0613)
OpenAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
gpt-oss-20B (high)
OpenAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Op GPT-3.5 Turbo (0613) | Op gpt-oss-20B (high) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.05/1M |
| Output Cost | $0.00/1M | $0.20/1M |
| Blended (3:1) | — | $0.09/1M |
| Specifications | ||
| Organization | OpenAI | OpenAI |
| Release Date | Jun 13, 2023 | Aug 5, 2025 |
| Performance & Speed | ||
| Throughput | — | 272.3 tok/s |
| TTFT | — | 412ms |
| Latency | — | 7757ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | — | 56.3 |
| Intelligence | — | 24.5 |
| Coding | — | 18.5 |
| Math | — | 89.3 |
| Standard Benchmarks | ||
| GPQA | — | 68.8% |
| MMLU Pro | — | 74.8% |
| HLE | — | 9.8% |
| LiveCodeBench | — | 77.7% |
| AIME 2025 | — | 89.3% |
| SciCode | — | 34.4% |
| LCR | — | 30.7% |
| IFBench | — | 65.1% |
| TAU-bench v2 | — | 60.2% |
| TerminalBench Hard | — | 10.6% |
Key Takeaways
GPT-3.5 Turbo (0613) offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
gpt-oss-20B (high) reaches a 18.5 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
GPT-3.5 Turbo (0613)
- Cost-sensitive applications
- High-volume processing
gpt-oss-20B (high)
- Code generation
- Software development
Recommended Comparisons
Popular alternatives 
