DeepSeek V4 Pro 0813 vs Mistral Large 4 vs Trinity Mini
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek V4 Pro 0813
53/100- ECI156.0
- Price$0.66 / $1.98
- Context1M
Mistral AI
Mistral Large 4
68/100- ECI154.6
- Price$0.70 / $2.10
- Context1.05M
Arcee AI
Trinity Mini
34/100- ECI—
- Price$0.045 / $0.15
- Context131K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Mistral Large 4 68/100, DeepSeek V4 Pro 0813 53/100, Trinity Mini 34/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 · DeepSeek V4 Pro 0813 $0.99 · Mistral Large 4 $1.05 per 1M tokens (3:1 blend)
- Longest contextMistral Large 4Mistral Large 4 1,048,576 · DeepSeek V4 Pro 0813 1,000,000 · Trinity Mini 131,072 tokens
- Widest inputsMistral Large 4DeepSeek V4 Pro 0813: Text · Mistral Large 4: Text, Images · Trinity Mini: Text
- Self-hostingDeepSeek V4 Pro 0813 and Trinity MiniPublishes downloadable weights (MIT and OpenMDW-1.1)
| Measure | Weight | DeepSeek V4 Pro 0813 | Mistral Large 4 | Trinity Mini |
|---|---|---|---|---|
| Inputs & features | 60% | 45 | 70 | 35 |
| Context window | 40% | 64 | 65 | 32 |
| Specs only | 100% | 53/100 | 68/100 | 34/100 |
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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 156.0 (best) | 154.6 | — |
| ECI rank | #42 of 158 (best) | #50 of 158 | — |
| GPQA DiamondGraduate-level science questions | 91.7% (best) | 90.2% | — |
| FrontierMath Tiers 1–3Research-level mathematics | 64.6% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.6% | 99.4% (best) | — |
| SimpleQA VerifiedShort factual questions | 52.9% (best) | 22.4% | — |
| Price per million tokens | |||
| Input | $0.66 | $0.70 | $0.045 (best) |
| Output | $1.98 | $2.10 | $0.15 (best) |
| Cached input | $0.022 (best) | $0.07 | — |
| Blended (3:1) | $0.99 | $1.05 | $0.071 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official DeepSeek API | Official Mistral API | Median of 1 providers |
| Limits | |||
| Context window | 1,000,000 tokens | 1,048,576 tokens (best) | 131,072 tokens |
| Max output | 384,000 tokens (best) | 262,144 tokens | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · high · max | Yeslow · medium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | OpenMIT | Proprietary | OpenOpenMDW-1.1 |
| API model ID | deepseek-v4-pro | mistral-large-4 | — |
| API providers | 54 (best) | 16 | 1 |
| Released | Aug 13, 2026 | Oct 6, 2026 | Dec 1, 2025 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
DeepSeek V4 Pro 0813$10.56
Mistral Large 4$11.20
Trinity Mini$0.75
Which should you choose?
Which is better: DeepSeek V4 Pro 0813, Mistral Large 4 or Trinity Mini?
There is not enough shared capability evidence to name an overall winner. The scores (Mistral Large 4 68/100, DeepSeek V4 Pro 0813 53/100, Trinity Mini 34/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, DeepSeek V4 Pro 0813, Mistral Large 4 or Trinity Mini?
Trinity Mini is cheaper at $0.045 input / $0.15 output per million tokens (median across 1 API provider). DeepSeek V4 Pro 0813 costs $0.66 input / $1.98 output per million tokens (official DeepSeek API price); Mistral Large 4 costs $0.70 input / $2.10 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.071 per million tokens for Trinity Mini versus $0.99 for DeepSeek V4 Pro 0813 (14× as much) and $1.05 for Mistral Large 4 (15× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek V4 Pro 0813 has an ECI of 156.0, Mistral Large 4 has an ECI of 154.6 and Trinity Mini has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Pro 0813, Mistral Large 4 and Trinity Mini 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?
Mistral Large 4 has the largest context window at 1,048,576 tokens, against 1,000,000 for DeepSeek V4 Pro 0813 and 131,072 for Trinity Mini. Maximum output per response: DeepSeek V4 Pro 0813 up to 384,000, Mistral Large 4 up to 262,144, Trinity Mini up to 131,072 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Pro 0813 accepts text; Mistral Large 4 accepts text and images; Trinity Mini accepts text. Mistral Large 4 handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Pro 0813 and Trinity Mini publishes its weights (MIT and OpenMDW-1.1) and can be self-hosted; Mistral Large 4 is proprietary.
Which is newer?
Mistral Large 4 is the newest, released Oct 6, 2026. DeepSeek V4 Pro 0813 came out Aug 13, 2026; Trinity Mini came out Dec 1, 2025.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 18, 2026.