MinerU2.5 2509 1.2B vs North Small Translate vs PaddleOCR VL
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Opendatalab
MinerU2.5 2509 1.2B
58/100- ECI—
- Price$0.024 / $0.071
- Context16K
Cohere
North Small Translate
50/100- ECI—
- PriceFree / Free
- Context16K
PaddlePaddle
PaddleOCR VL
64/100- ECI—
- Price$0.02 / $0.02
- Context131K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (PaddleOCR VL 64/100, MinerU2.5 2509 1.2B 58/100, North Small Translate 50/100) compare the available specifications and price. 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 priceNorth Small TranslateNorth Small Translate Free · PaddleOCR VL $0.02 · MinerU2.5 2509 1.2B $0.036 per 1M tokens (3:1 blend)
- Longest contextPaddleOCR VLPaddleOCR VL 131,072 · MinerU2.5 2509 1.2B 16,384 · North Small Translate 16,000 tokens
- Widest inputsMinerU2.5 2509 1.2B and PaddleOCR VLMinerU2.5 2509 1.2B: Text, Images · North Small Translate: Text · PaddleOCR VL: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | MinerU2.5 2509 1.2B | North Small Translate | PaddleOCR VL |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 25 | 0 | 25 |
| Context window | 20% | 0 | 0 | 32 |
| Specs & price only | 100% | 58/100 | 50/100 | 64/100 |
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 | MinerU2.5 2509 1.2BOpendatalab | PaddleOCR VLPaddlePaddle | |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.024 | Free (best) | $0.02 |
| Output | $0.071 | Free (best) | $0.02 |
| Cached input | — | — | — |
| Blended (3:1) | $0.036 | Free (best) | $0.02 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Cohere API | Median of 1 providers |
| Limits | |||
| Context window | 16,384 tokens | 16,000 tokens | 131,072 tokens (best) |
| Max output | — | 16,000 tokens | 16,384 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | No | No | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenAGPL-3.0 | OpenCC-BY-NC-4.0 | OpenApache-2.0 |
| API model ID | — | north-small-translate-09-2026 | — |
| API providers | 1 | 1 | 1 |
| Released | Sep 17, 2025 | Sep 9, 2026 | Oct 16, 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.
- MinerU2.5 2509 1.2B$0.381
North Small TranslateFree
- PaddleOCR VL$0.24
Which should you choose?
Which is better: MinerU2.5 2509 1.2B, North Small Translate or PaddleOCR VL?
There is not enough shared capability evidence to name an overall winner. The scores (PaddleOCR VL 64/100, MinerU2.5 2509 1.2B 58/100, North Small Translate 50/100) compare the available specifications and price. 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, MinerU2.5 2509 1.2B, North Small Translate or PaddleOCR VL?
North Small Translate is cheaper at Free input / Free output per million tokens (official Cohere API price). PaddleOCR VL costs $0.02 input / $0.02 output per million tokens (median across 1 API provider); MinerU2.5 2509 1.2B costs $0.024 input / $0.071 output per million tokens (median across 1 API provider). North Small Translate is listed as free.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MinerU2.5 2509 1.2B has not been scored yet, North Small Translate has not been scored yet and PaddleOCR VL has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MinerU2.5 2509 1.2B, North Small Translate and PaddleOCR VL yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that MinerU2.5 2509 1.2B, North Small Translate and PaddleOCR VL does not support tool calling, which most coding agents need.
Which has the bigger context window?
PaddleOCR VL has the largest context window at 131,072 tokens, against 16,384 for MinerU2.5 2509 1.2B and 16,000 for North Small Translate. Maximum output per response: North Small Translate up to 16,000, PaddleOCR VL up to 16,384 tokens.
Which can read images, PDFs, audio or video?
MinerU2.5 2509 1.2B accepts text and images; North Small Translate accepts text; PaddleOCR VL accepts text and images. MinerU2.5 2509 1.2B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (AGPL-3.0, CC-BY-NC-4.0 and Apache-2.0), so you can self-host them.
Which is newer?
North Small Translate is the newest, released Sep 9, 2026. PaddleOCR VL came out Oct 16, 2025; MinerU2.5 2509 1.2B came out Sep 17, 2025.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.