Model Comparison
GPT-5.5 (Non-reasoning)
vs. gpt-oss-120b (low)
Comparing 2 AI models · 10 benchmarks · OpenAI
Recommended Pick
Op GPT-5.5 (Non-reasoning) 9 metric wins Strongest on: Latency, Intelligence, Coding
Best Value
gpt-oss-120b (low)
100.0 value score
46.1 reasoning / $0.26/1M
Lowest Price
gpt-oss-120b (low)
$0.15/1M input price
Best Reasoning
gpt-oss-120b (low)
46.1 reasoning score
Blends available reasoning benchmarks
Best for Coding
GPT-5.5 (Non-reasoning)
48.6 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
gpt-oss-120b (low) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
gpt-oss-120b (low) is 33.3x cheaper on input tokens than GPT-5.5 (Non-reasoning).
Speed gap
gpt-oss-120b (low) generates about 6.5x as many tokens per second as GPT-5.5 (Non-reasoning).
Reasoning gap
gpt-oss-120b (low) leads GPT-5.5 (Non-reasoning) by 2.6 points on reasoning.
Coding gap
GPT-5.5 (Non-reasoning) leads gpt-oss-120b (low) by 33.1 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
GPT-5.5 (Non-reasoning)
OpenAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
gpt-oss-120b (low)
OpenAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Op GPT-5.5 (Non-reasoning) | Op gpt-oss-120b (low) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $5.00/1M | $0.15/1M |
| Output Cost | $30.00/1M | $0.60/1M |
| Blended (3:1) | $11.25/1M | $0.26/1M |
| Specifications | ||
| Organization | OpenAI | OpenAI |
| Release Date | Apr 23, 2026 | Aug 5, 2025 |
| Performance & Speed | ||
| Throughput | 54.0 tok/s | 352.1 tok/s |
| TTFT | 1007ms | 498ms |
| Latency | 1007ms | 6178ms |
| Composite Indices | ||
| Value Score | 2.2 | 100.0 |
| Reasoning Score | 43.4 | 46.1 |
| Intelligence | 40.9 | 24.5 |
| Coding | 48.6 | 15.5 |
| Math | — | 66.7 |
| Standard Benchmarks | ||
| GPQA | 76.8% | 67.2% |
| MMLU Pro | — | 77.5% |
| HLE | 12.6% | 5.2% |
| LiveCodeBench | — | 70.7% |
| AIME 2025 | — | 66.7% |
| SciCode | 47.3% | 36.0% |
| LCR | 56.3% | 43.7% |
| IFBench | 46.1% | 58.3% |
| TAU-bench v2 | 69.3% | 45.0% |
| TerminalBench Hard | 49.2% | 5.3% |
Key Takeaways
gpt-oss-120b (low) offers the best value at $0.15/1M, making it ideal for high-volume applications and cost-conscious projects.
gpt-oss-120b (low) has the strongest reasoning profile with a 46.1 reasoning score, combining the available reasoning-heavy benchmarks.
GPT-5.5 (Non-reasoning) reaches a 48.6 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-5.5 (Non-reasoning)
- Code generation
- Software development
gpt-oss-120b (low)
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
