ERNIE-4.5-0.3B-PT vs ERNIE 5.1
Benchmark Performance
Available Benchmarks
Technical Differences
Side-by-Side Facts
| Field | ERNIE-4.5-0.3B-PT | ERNIE 5.1 |
|---|---|---|
| Developer | Baidu | Baidu |
| Family | Ernie 4 5 0 3b Pt | Ernie 5 |
| Model | ERNIE-4.5-0.3B-PT | ERNIE 5.1 |
| Version | ERNIE-4.5-0.3B-PT | ERNIE 5.1 |
| Lifecycle | active | active |
| Released | Unknown | Unknown |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
| Context window | 131,072 | 131,072 |
| Total parameters | 360,748,032 | Unknown |
| Active parameters | Unknown | Unknown |
| License | apache-2.0 | Unknown |
| Open weights | Yes | No |
| API available | Unknown | Yes |
| Self-hostable | Yes | No |
| Provider access | Unknown | Baidu Qianfan (Standard) |
| Capabilities | chat, generation | agents, chat, reasoning, search, tools |
11 comparable fields · 6 material differences · Pair passes the primary-source comparison gate
ERNIE-4.5-0.3B-PT Capabilities
ERNIE 5.1 Capabilities
Internal Comparison Graph
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
ERNIE 5.1Baidu | vs | ERNIE X1.1Baidu | family variantstext |
ERNIE 5.1Baidu | vs |  Sonar Deep ResearchPerplexity | cross-developer peerstext |
ERNIE 5.1Baidu | vs | Sonar Reasoning ProPerplexity | cross-developer peerstext |
ERNIE 5.1Baidu | vs |  GLM-5.3Z.ai | cross-developer peerstext |
ERNIE 5.1Baidu | vs |  Command ACohere | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs | ERNIE X1.1Baidu | family variantstext |
ERNIE 5.1Baidu | vs | SonarPerplexity | cross-developer peerstext |
ERNIE 5.1Baidu | vs | Sonar ProPerplexity | cross-developer peerstext |
ERNIE 5.1Baidu | vs |  Hy4 previewTencent | cross-developer peerstext |
ERNIE 5.1Baidu | vs |  DeepSeek-V4-Flash-Vision-ExpDeepSeek | cross-developer peerstext |
ERNIE 5.1Baidu | vs |  Antigravity AgentGoogle DeepMind | cross-developer peerstext |
PaddleOCR-VL-1.5Baidu | vs | ERNIE-4.5-0.3B-PTBaidu | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
ERNIE-4.5-0.3B-PT vs ERNIE 5.1 FAQs
Is ERNIE-4.5-0.3B-PT or ERNIE 5.1 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both ERNIE-4.5-0.3B-PT and ERNIE 5.1, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, ERNIE-4.5-0.3B-PT or ERNIE 5.1?+
Only ERNIE 5.1 has a directly sourced input price: $4.00 per million tokens. Only ERNIE 5.1 has a directly sourced output price: $18.00 per million tokens.
Which has a larger context window, ERNIE-4.5-0.3B-PT or ERNIE 5.1?+
Neither model has a larger sourced context window in this comparison. ERNIE-4.5-0.3B-PT is 131,072 and ERNIE 5.1 is 131,072.
Which performs better in benchmarks, ERNIE-4.5-0.3B-PT or ERNIE 5.1?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can ERNIE-4.5-0.3B-PT or ERNIE 5.1 be self-hosted?+
ERNIE-4.5-0.3B-PT is the only model in this pair currently marked as self-hostable. ERNIE-4.5-0.3B-PT is open weight; ERNIE 5.1 is not marked open weight.
Can ERNIE-4.5-0.3B-PT and ERNIE 5.1 understand images?+
ERNIE-4.5-0.3B-PT is not documented with image input; ERNIE 5.1 is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, ERNIE-4.5-0.3B-PT or ERNIE 5.1?+
Neither has a larger sourced maximum output. ERNIE-4.5-0.3B-PT is — and ERNIE 5.1 is 65,536.
Do ERNIE-4.5-0.3B-PT and ERNIE 5.1 support reasoning and tool use?+
ERNIE-4.5-0.3B-PT: none of these features are definitively sourced. ERNIE 5.1: reasoning and tool calling. Feature support does not establish relative quality.
Which is available from more inference providers, ERNIE-4.5-0.3B-PT or ERNIE 5.1?+
ERNIE-4.5-0.3B-PT has 0 sourced provider routes; ERNIE 5.1 has 1, so ERNIE 5.1 has broader tracked availability.
Which offers better value, ERNIE-4.5-0.3B-PT or ERNIE 5.1?+
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.