Compare / head-to-head
ERNIE 5.0vsStep 3.5 Flash
Step 3.5 Flash leads 4 of 4 shared benchmarks. Step 3.5 Flash has the larger context window (256K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 4
Step 3.5 Flash leads
Cheaper per token
—
list price, input + output
Larger context
Step 3.5 Flash
256K tokens
Provider uptime (30d)
— · —
Baidu · StepFun
ERNIE 5.0
Baidu · released 2026-02-06
textvision
- Context
- 128K
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 21 · 5 core
Step 3.5 Flash
StepFun · released 2026-02-12
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 18 · 5 core
Quality
Benchmark matrix
4 shared · 17 only ERNIE 5.0 · 13 only Step 3.5 Flash| Benchmark | ERNIE 5.0 | Step 3.5 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| AIME 2025 | 89.06% ↗ | 97.3% ↗ | -8.2 pt | Step 3.5 Flash |
| BrowseComp-ZH | 64.71% ↗ | 66.9% ↗ | -2.2 pt | Step 3.5 Flash |
| LiveCodeBench v6 | 76.21% ↗ | 86.4% ↗ | -10.2 pt | Step 3.5 Flash |
| Tau2-Bench | 78.79% ↗ | 88.2% ↗ | -9.4 pt | Step 3.5 Flash |
| Only ERNIE 5.0 reports · 17 | ||||
| GPQA Diamond | 86.36% ↗ | not reported | — | — |
| MMLU-Pro | 83.8% ↗ | not reported | — | — |
| ACEBench Chinese | 89.6% ↗ | not reported | — | — |
| ACEBench English | 87.7% ↗ | not reported | — | — |
| BBEH | 66.63% ↗ | not reported | — | — |
| BFCL v4 | 66.47% ↗ | not reported | — | — |
| ChineseSimpleQA | 86.03% ↗ | not reported | — | — |
| HMMT 2025 | 79.58% ↗ | not reported | — | — |
| HumanEval+ | 94.48% ↗ | not reported | — | — |
| Humanity's Last Exam | 25.81% ↗ | not reported | — | — |
| IFEval | 93.35% ↗ | not reported | — | — |
| MBPP+ | 82.54% ↗ | not reported | — | — |
| Multi-IF | 85.56% ↗ | not reported | — | — |
| MultiChallenge | 65.98% ↗ | not reported | — | — |
| SimpleQA | 74.01% ↗ | not reported | — | — |
| SpreadsheetBench | 40.08% ↗ | not reported | — | — |
| ZebraLogic | 96.5% ↗ | not reported | — | — |
| Only Step 3.5 Flash reports · 13 | ||||
| SWE-bench Verified | not reported | 74.4% ↗ | — | — |
| AIME 2026 | not reported | 96.7% ↗matharena | — | — |
| LMArena Elo | not reported | 1403.7 ↗ | — | — |
| BrowseComp | not reported | 51.6% ↗ | — | — |
| BrowseComp (with context manager) | not reported | 69% ↗ | — | — |
| BrowseComp-ZH (with context manager) | not reported | 73.7% ↗ | — | — |
| GAIA (no file) | not reported | 84.5% ↗ | — | — |
| HMMT 2025 (Feb/Nov average) | not reported | 96.2% ↗ | — | — |
| IMOAnswerBench | not reported | 85.4% ↗ | — | — |
| ResearchRubrics | not reported | 65.3% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 51% ↗ | — | — |
| xbench-DeepSearch 2025.05 | not reported | 83.7% ↗ | — | — |
| xbench-DeepSearch 2025.10 | not reported | 56.3% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is ERNIE 5.0 minus Step 3.5 Flash in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | ERNIE 5.0 | Step 3.5 Flash | Edge |
|---|---|---|---|
| Context window | 128K tokens | 256K tokens | Step 3.5 Flash |
| Max output | 66K tokens | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text · vision | text | ERNIE 5.0 |
| Released | 2026-02-06 | 2026-02-12 | — |
| Cited benchmark scores | 21 | 18 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
ERNIE 5.0 vs …
Models sharing the most benchmarksMore matchups
Step 3.5 Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run ERNIE 5.0 and Step 3.5 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.