LLM Comparison
DeepSeek V3.2 Speciale vs GPT-5.6 Luna
Side-by-side specs, pricing & capabilities · Updated September 2026
Price vs Intelligence
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 66 82.0 | 52 74.7 |
| Family | DeepSeek | GPT-5.6 |
| Status | Current | Current |
| Release Date | Dec 2025 | Jul 2026 |
| Context Window | 164K tokens | 1.1M tokens |
| Input Price | $0.40/M tokens | $0.20/M tokens |
| Output Price | $1.20/M tokens | $1.20/M tokens |
| Pricing Notes | Cache read: $0.2000/M tokens | OpenAI pricing page lists $1 input and $6 output per 1M tokens, plus GPT-5.6 cache-write and cache-read pricing. |
| Capabilities | textcode | textvisionreasoningcodingtool-useweb-searchfile-searchcomputer-useagents |
| Training Cutoff | — | Feb 16, 2026 |
| Max Output | 164K tokens | 128K tokens |
| API Identifier | deepseek/deepseek-v3.2-speciale | gpt-5.6-luna |
| Benchmarks | ||
| MMLU-Pro | 85deepseek | — |
| AIME 2025 | 96deepseek | — |
| LiveCodeBench | 88.7deepseek | — |
| HLE | 30.6deepseek | — |
| HMMT 2025 | 99deepseek | — |
| SWE-bench Verified | 73deepseek | — |
| Terminal-Bench 2.0 | 46deepseek | — |
| GPQA Diamond | 87.0707artificial-analysis | 91.1111artificial-analysis |
| Artificial Analysis Intelligence Index | — | 51artificial-analysis |
| Artificial Analysis Coding Agent Index | — | 74.6artificial-analysis |
| Artificial Analysis Intelligence Index v4.3 | — | 37.5048artificial-analysis |
| SciCode | — | 53.588artificial-analysis |
| Terminal-Bench 2.1 | — | 80.8989artificial-analysis |
| View DeepSeek V3.2 Speciale | View GPT-5.6 Luna | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| GPT-5.6 LunaCheapest | $0.20 | $0.60 | $0.80 | — |
| DeepSeek V3.2 Speciale | $0.40 | $0.60 | $1.00 | +25% |
DeepSeek
DeepSeek V3.2 Speciale
DeepSeek V3.2 Speciale is a large language model from DeepSeek. Supports up to 163,840 token context window. Achieves 87.1% on MMLU. Available from $0.40/M input tokens.
OpenAI
GPT-5.6 Luna
GPT-5.6 Luna is OpenAI lower-cost GPT-5.6 model for high-volume reasoning, coding, and agentic workloads. OpenAI model docs list the same 1.05M token context window, 128K max output, and major tool support as the larger GPT-5.6 variants.
More Comparisons
Looking for more AI models?
Browse All LLMs