DeepSeek-V4-Flash vs Trinity Large Thinking
DeepSeek vs Arcee AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 75.2)
- •DeepSeek-V4-Flash is cheaper ($0.10 vs $0.22 per 1M input)
- •Trinity Large Thinking is faster
- •DeepSeek-V4-Flash has a larger context window (1M)
| DeepSeek-V4-Flash | Trinity Large Thinking | |
|---|---|---|
| Intelligence index | 89.4 | 75.2 |
| Developer | DeepSeek | Arcee AI |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Input price | $0.10 / 1M | $0.22 / 1M |
| Output price | $0.20 / 1M | $0.85 / 1M |
| Speed | 109 tok/s | 129 tok/s |
| Released | April 24, 2026 | April 1, 2026 |
| Parameters | 284B (13B active) | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-V4-Flash
Trinity Large Thinking
GPQA Diamond
89.4
75.2
Humanity’s Last Exam
32.1
14.7