Gemini 2.5 Flash vs Trinity Mini vs DeepSeek R1 0528
Too close to call on our weighted score (Gemini 2.5 Flash 68, Trinity Mini 65, DeepSeek R1 0528 41). The right pick depends on what you value most.
GoogleGemini 2.5 Flash
68/100- ECI140.6
- Price$0.30 / $2.50
- Context1.05M
Arcee AITrinity Mini
65/100- ECI—
- Price$0.045 / $0.15
- Context131K
DeepSeekDeepSeek R1 0528
41/100- ECI141.2
- Price$0.512 / $2.19
- Context164K
Too close to call
It is close. Our weighted score puts them within 2 points (Gemini 2.5 Flash 68/100, Trinity Mini 65/100, DeepSeek R1 0528 41/100), so choose by what matters most for your work: Trinity Mini on price and Gemini 2.5 Flash for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceTrinity MiniTrinity Mini $0.071 · Gemini 2.5 Flash $0.85 · DeepSeek R1 0528 $0.932 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 FlashGemini 2.5 Flash 1,048,576 · DeepSeek R1 0528 163,840 · Trinity Mini 131,072 tokens
- Widest inputsGemini 2.5 FlashGemini 2.5 Flash: Text, Images, PDFs, Audio, Video · Trinity Mini: Text · DeepSeek R1 0528: Text
- Self-hostingTrinity Mini and DeepSeek R1 0528Publishes downloadable weights (OpenMDW-1.1 and MIT)
| Measure | Weight | Gemini 2.5 Flash | Trinity Mini | DeepSeek R1 0528 |
|---|---|---|---|---|
| Price | 50% | 51 | 100 | 49 |
| Inputs & features | 30% | 100 | 35 | 35 |
| Context window | 20% | 61 | 25 | 28 |
| Overall | 100% | 68/100 | 65/100 | 41/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemini 2.5 FlashGoogle | Trinity MiniArcee AI | DeepSeek R1 0528DeepSeek |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 140.6 | — | 141.2 (best) |
| ECI rank | #110 of 165 | — | #108 of 165 (best) |
| GPQA DiamondGraduate-level science questions | — | — | 76.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 66.4% |
| Price per million tokens | |||
| Input | $0.30 | $0.045 (best) | $0.512 |
| Output | $2.50 | $0.15 (best) | $2.19 |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.85 | $0.071 (best) | $0.932 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Google API | Median of 1 providers | Median of 16 providers |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 131,072 tokens | 163,840 tokens |
| Max output | 65,536 tokens | 131,072 tokens (best) | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | OpenOpenMDW-1.1 | OpenMIT |
| API model ID | gemini-2.5-flash | — | — |
| API providers | 32 (best) | 1 | 16 |
| Released | Jun 17, 2025 | Dec 1, 2025 | May 28, 2025 |
| Knowledge cutoff | Jan 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini 2.5 Flash$8.00
- Trinity Mini$0.75
- DeepSeek R1 0528$9.50
Which should you choose?
Which is better: Gemini 2.5 Flash, Trinity Mini or DeepSeek R1 0528?
It is close. Our weighted score puts them within 2 points (Gemini 2.5 Flash 68/100, Trinity Mini 65/100, DeepSeek R1 0528 41/100), so choose by what matters most for your work: Trinity Mini on price and Gemini 2.5 Flash for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Gemini 2.5 Flash, Trinity Mini or DeepSeek R1 0528?
Trinity Mini is cheaper at $0.045 input / $0.15 output per million tokens (median across 1 API provider). Gemini 2.5 Flash costs $0.30 input / $2.50 output per million tokens (official Google API price); DeepSeek R1 0528 costs $0.512 input / $2.19 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.071 per million tokens for Trinity Mini versus $0.85 for Gemini 2.5 Flash (12× as much) and $0.932 for DeepSeek R1 0528 (13× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemini 2.5 Flash has an ECI of 140.6, Trinity Mini has not been scored yet and DeepSeek R1 0528 has an ECI of 141.2.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 2.5 Flash, Trinity Mini and DeepSeek R1 0528 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 2.5 Flash has the largest context window at 1,048,576 tokens, against 163,840 for DeepSeek R1 0528 and 131,072 for Trinity Mini. Maximum output per response: Gemini 2.5 Flash up to 65,536, Trinity Mini up to 131,072, DeepSeek R1 0528 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Flash accepts text, images, PDFs, audio and video; Trinity Mini accepts text; DeepSeek R1 0528 accepts text. Gemini 2.5 Flash handles the widest range of inputs.
Are any of these open source?
Trinity Mini and DeepSeek R1 0528 publishes its weights (OpenMDW-1.1 and MIT) and can be self-hosted; Gemini 2.5 Flash is proprietary.
Which is newer?
Trinity Mini is the newest, released Dec 1, 2025. Gemini 2.5 Flash came out Jun 17, 2025; DeepSeek R1 0528 came out May 28, 2025. Knowledge cutoff: Gemini 2.5 Flash Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
Related comparisons
- Gemini 2.5 Flash vs Kimi K2 InstructMoonshot AI · ECI 139.9
- Gemini 2.5 Flash vs Qwen3 235B-A22B Thinking 2507Alibaba (Qwen) · ECI 143.8
- Gemini 2.5 Flash vs GPT-5 MiniOpenAI · ECI 145.4
- Trinity Mini vs Qwen3 VL Flash (Alibaba Cloud)Alibaba (Qwen)
- Trinity Mini vs AutoGLM Phone 9B MultilingualZ.ai (Zhipu)
- Trinity Mini vs Ministral 3 3BMistral AI
