PaddleOCR VL 1.5 vs Granite Embedding 311m Multilingual r2
At a Glance
| Compare |  PaddleOCR VL 1.5Baidu | |
|---|---|---|
| Pricing and Limits | ||
| Context windowMaximum documented tokens | 131K | 33K |
| Model facts checked | Aug 28, 2026View model evidence → | Aug 28, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | PaddleOCR-VL-1.5 | granite-embedding-311m-multilingual-r2 |
|---|---|---|
| Developer | Baidu | IBM |
| Family | Paddleocr VL 1 5 | Granite Embedding 311m Multilingual R2 |
| Model | PaddleOCR-VL-1.5 | granite-embedding-311m-multilingual-r2 |
| Version | PaddleOCR-VL-1.5 | granite-embedding-311m-multilingual-r2 |
| Lifecycle | active | active |
| Released | 2026-01-29 | 2026-04-29 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Embedding |
| Context window | 131K | 33K |
| Total parameters | 958.6M | 311.7M |
| Active parameters | Unknown | Unknown |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Unknown | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Hugging Face (Standard) |
| Capabilities | chat, generation | embeddings |
PaddleOCR VL 1.5 Capabilities
Granite Embedding 311m Multilingual r2 Capabilities
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
PaddleOCR-VL-1.5Baidu | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
PaddleOCR-VL-1.5Baidu | vs | Claude Fable 5.1Anthropic | cross-developer peersimage, text |
PaddleOCR-VL-1.5Baidu | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
PaddleOCR-VL-1.5Baidu | vs |  DeepSeek-V4.1-FlashDeepSeek | cross-developer peersimage, text |
PaddleOCR-VL-1.5Baidu | vs | Grok 4.6xAI | cross-developer peersimage, text |
PaddleOCR-VL-1.5Baidu | vs |  Qwen3.8-MaxQwen | cross-developer peersimage, text |
PaddleOCR-VL-1.5Baidu | vs |  Kimi-K3Moonshot AI | cross-developer peersimage, text |
 MiniMax-M3MiniMax | vs | PaddleOCR-VL-1.5Baidu | cross-developer peersimage, text |
PaddleOCR-VL-1.5Baidu | vs |  GLM-5.3Z.ai | cross-developer peerstext |
PaddleOCR-VL-1.5Baidu | vs |  Hy4 previewTencent | cross-developer peerstext |
PaddleOCR-VL-1.5Baidu | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text |
PaddleOCR-VL-1.5Baidu | vs |  Mistral Large 3Mistral AI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
PaddleOCR VL 1.5 vs Granite Embedding 311m Multilingual r2 FAQs
Is PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both PaddleOCR VL 1.5 and Granite Embedding 311m Multilingual r2, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2?+
Neither model has a directly sourced input price in this comparison. Neither model has a directly sourced output price in this comparison.
Which has a larger context window, PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2?+
PaddleOCR VL 1.5 has the larger sourced context window. PaddleOCR VL 1.5 supports 131K and Granite Embedding 311m Multilingual r2 supports 33K.
Which performs better in benchmarks, PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2 be self-hosted?+
Both models have the same recorded self-hosting status: supported. PaddleOCR VL 1.5 is open weight; Granite Embedding 311m Multilingual r2 is open weight.
Can PaddleOCR VL 1.5 and Granite Embedding 311m Multilingual r2 understand images?+
PaddleOCR VL 1.5 is documented with image input; Granite Embedding 311m Multilingual r2 is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2?+
Neither has a larger sourced maximum output. PaddleOCR VL 1.5 is — and Granite Embedding 311m Multilingual r2 is —.
Do PaddleOCR VL 1.5 and Granite Embedding 311m Multilingual r2 support reasoning and tool use?+
PaddleOCR VL 1.5: image input. Granite Embedding 311m Multilingual r2: none of these features are definitively sourced. Feature support does not establish relative quality.
Which is available from more inference providers, PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2?+
PaddleOCR VL 1.5 has 0 sourced provider routes; Granite Embedding 311m Multilingual r2 has 1, so Granite Embedding 311m Multilingual r2 has broader tracked availability.
Which offers better value, PaddleOCR VL 1.5 or Granite Embedding 311m Multilingual r2?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.