Compare / head-to-head
DeepSeek V3.2vsERNIE 5.0
DeepSeek V3.2 leads 2 of 3 shared benchmarks. DeepSeek V3.2 has the larger context window (131K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 1
DeepSeek V3.2 leads
Cheaper per token
—
list price, input + output
Larger context
DeepSeek V3.2
131K tokens
Provider uptime (30d)
100% · —
DeepSeek · Baidu
DeepSeek V3.2
DeepSeek · released 2025-12-01
text
- Context
- 131K
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 8 · 7 core
ERNIE 5.0
Baidu · released 2026-02-06
textvision
- Context
- 128K
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 21 · 5 core
Quality
Benchmark matrix
3 shared · 4 only DeepSeek V3.2 · 18 only ERNIE 5.0| Benchmark | DeepSeek V3.2 | ERNIE 5.0 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| GPQA Diamond | 82.4% ↗ | 86.36% ↗ | -4 pt | ERNIE 5.0 |
| MMLU-Pro | 85% ↗ | 83.8% ↗ | +1.2 pt | DeepSeek V3.2 |
| AIME 2025 | 93.1% ↗ | 89.06% ↗ | +4 pt | DeepSeek V3.2 |
| Only DeepSeek V3.2 reports · 4 | ||||
| SWE-bench Verified | 73.1% ↗ | not reported | — | — |
| AIME 2026 | 94.2% ↗matharena | not reported | — | — |
| Humanity's Last Exam (no tools) | 25.1% ↗ | not reported | — | — |
| LMArena Elo | 1424.8 ↗ | not reported | — | — |
| Only ERNIE 5.0 reports · 18 | ||||
| ACEBench Chinese | not reported | 89.6% ↗ | — | — |
| ACEBench English | not reported | 87.7% ↗ | — | — |
| BBEH | not reported | 66.63% ↗ | — | — |
| BFCL v4 | not reported | 66.47% ↗ | — | — |
| BrowseComp-ZH | not reported | 64.71% ↗ | — | — |
| ChineseSimpleQA | not reported | 86.03% ↗ | — | — |
| HMMT 2025 | not reported | 79.58% ↗ | — | — |
| HumanEval+ | not reported | 94.48% ↗ | — | — |
| Humanity's Last Exam | not reported | 25.81% ↗ | — | — |
| IFEval | not reported | 93.35% ↗ | — | — |
| LiveCodeBench v6 | not reported | 76.21% ↗ | — | — |
| MBPP+ | not reported | 82.54% ↗ | — | — |
| Multi-IF | not reported | 85.56% ↗ | — | — |
| MultiChallenge | not reported | 65.98% ↗ | — | — |
| SimpleQA | not reported | 74.01% ↗ | — | — |
| SpreadsheetBench | not reported | 40.08% ↗ | — | — |
| Tau2-Bench | not reported | 78.79% ↗ | — | — |
| ZebraLogic | not reported | 96.5% ↗ | — | — |
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 DeepSeek V3.2 minus ERNIE 5.0 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 | DeepSeek V3.2 | ERNIE 5.0 | Edge |
|---|---|---|---|
| Context window | 131K tokens | 128K tokens | DeepSeek V3.2 |
| Max output | 66K tokens | 66K tokens | Tie |
| 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 | text · vision | ERNIE 5.0 |
| Released | 2025-12-01 | 2026-02-06 | — |
| Cited benchmark scores | 8 | 21 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
DeepSeek V3.2 vs …
Models sharing the most benchmarksMore matchups
ERNIE 5.0 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3.2 and ERNIE 5.0 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.