ERNIE 5.0 vs Step 5 Preview
Baidu · China | StepFun · China · Updated June 2026
Quick verdict
Pick ERNIE 5.0 for baidu's flagship omni-modal model — text, image and video understanding or particularly strong on chinese-language reasoning tasks. Pick Step 5 Preview for sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents or 1m-token context window (64k max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available. On a tight budget at scale, ERNIE 5.0 is the value pick.
ERNIE 5.0 (Baidu) and Step 5 Preview (StepFun) are two of the models people most often weigh against each other in 2026. ERNIE 5.0 is baidu's flagship omni-modal ERNIE model — strong Chinese-language and multimodal reasoning at low cost, though it trails the Western frontier on independent benchmarks. Step 5 Preview is stepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: ERNIE 5.0 is about 1.7× cheaper on input ($0.6/$2.1 per 1M tokens vs $1/$2.7 per 1M tokens) — modest, but it adds up at steady volume.
- ▸Context window: Step 5 Preview holds 7.8× more — 1M tokens (~1,500 pages) vs 128K (~192 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
- ▸Recency: Step 5 Preview is the newer model by about 8 months (released September 20, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | ERNIE 5.0 | Step 5 Preview |
|---|---|---|
| Provider | Baidu (China) | StepFun (China) |
| Released | January 22, 2026 | September 20, 2026 |
| Context window | 128K (~192 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | $0.6/$2.1 per 1M tokens | $1/$2.7 per 1M tokens |
| Open weight? | No — API only | No — API only |
| Modalities | text, image, video, code | text, image, code |
| SWE-Bench Verified | Not published | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
Baidu's flagship omni-modal model — text, image and video understanding
ERNIE 5.0
Step 5 Preview is comparatively weak here — trails closed frontier models on coding — 67.7% on DeepSWE v1.1 vs GPT-6 Astra's 74.1% and Claude Opus 5's 74.0%
Particularly strong on Chinese-language reasoning tasks
ERNIE 5.0
Baidu's flagship omni-modal ERNIE model — strong Chinese-language and multimodal reasoning at low cost, though it trails the Western frontier on independent benchmarks — and it runs cheaper at $0.6/$2.1 per 1M tokens.
Competitive API pricing (around $0.60/$2.10 per million tokens)
ERNIE 5.0
Step 5 Preview is comparatively weak here — a 'Preview' release, not StepFun's finished flagship — positioning and pricing may change once weights ship
Sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents
Step 5 Preview
Its 1M tokens window holds about 7.8× more than ERNIE 5.0's 128K in a single prompt.
1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available
Step 5 Preview
ERNIE 5.0 is comparatively weak here — trails the Western frontier on aggregate independent tests (AA Intelligence Index ~22 for the tracked Thinking Preview)
67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%)
Step 5 Preview
ERNIE 5.0 is comparatively weak here — closed weights on a China-hosted API
Lowest cost at scale
ERNIE 5.0
At $0.6/$2.1 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Largest single-prompt input
Step 5 Preview
Its 1M tokens window is about 7.8× larger than ERNIE 5.0's 128K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume
→ ERNIE 5.0
At $0.6/$2.1 per 1M tokens it undercuts Step 5 Preview, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ Step 5 Preview
Larger 1M tokens window fits more in one prompt.
Anyone whose priority is baidu's flagship omni-modal model — text, image and video understanding
→ ERNIE 5.0
It is specifically built for that.
Anyone whose priority is sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents
→ Step 5 Preview
That is its strongest area.
ERNIE 5.0: where it fits
Baidu's flagship omni-modal ERNIE model — strong Chinese-language and multimodal reasoning at low cost, though it trails the Western frontier on independent benchmarks. Released January 22, 2026 by Baidu, it is built for baidu's flagship omni-modal model — text, image and video understanding, particularly strong on Chinese-language reasoning tasks, competitive API pricing (around $0.60/$2.10 per million tokens), and backed by a major lab with deep China-market integration.
Its trade-offs are real: trails the Western frontier on aggregate independent tests (AA Intelligence Index ~22 for the tracked Thinking Preview), parameter and architecture details are vendor-stated and opaque, closed weights on a China-hosted API, and 128K context is smaller than 1M-token rivals. At $0.6 in / $2.1 out per million tokens, it sits in the budget price band.
Step 5 Preview: where it fits
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. Released September 20, 2026 by StepFun, it is built for sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents, 1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available, 67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%), and scores 44 on the Artificial Analysis Intelligence Index, ranking 27th of 653 models tracked.
Its trade-offs: trails closed frontier models on coding — 67.7% on DeepSWE v1.1 vs GPT-6 Astra's 74.1% and Claude Opus 5's 74.0%, open weights were promised for October 15, 2026 but hadn't shipped as of this writing — API-only for now despite the open-weight roadmap, a 'Preview' release, not StepFun's finished flagship — positioning and pricing may change once weights ship, and stepCodeBench and DeepSWE figures are StepFun's own reported numbers, not yet independently reproduced at scale. At $1 in / $2.7 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
ERNIE 5.0 and Step 5 Preview overlap enough that the right pick depends on your specific job. ERNIE 5.0 costs less per token; Step 5 Preview holds the larger context; and each leads in its own area — ERNIE 5.0 for baidu's flagship omni-modal model — text, image and video understanding, Step 5 Preview for sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both ERNIE 5.0 and Step 5 Preview without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
See pricingFrequently asked questions
Is ERNIE 5.0 or Step 5 Preview better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, ERNIE 5.0 leans toward baidu's flagship omni-modal model — text, image and video understanding while Step 5 Preview leans toward sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, ERNIE 5.0 or Step 5 Preview?
ERNIE 5.0 is cheaper — $0.6/$2.1 per 1M tokens vs $1/$2.7 per 1M tokens, roughly 1.7× apart on input.
Which has the bigger context window?
Step 5 Preview — 1M tokens vs 128K, about 7.8× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both ERNIE 5.0 and Step 5 Preview together?
Yes — a multi-model platform like LumiChats gives you ERNIE 5.0, Step 5 Preview and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, ERNIE 5.0 or Step 5 Preview?
Step 5 Preview — released September 20, 2026, about 8 months after ERNIE 5.0.
Related comparisons
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.