Skip to main content

DeepSeek V3.2-Exp vs ERNIE 5.0

SpecDeepSeek V3.2-ExpERNIE 5.0
Respan Index21.8 (#121)22.2 (#118)
Blended price per 1M$0.305-
Context window128K128K
Input / output per 1M$0.27 / $0.41-
Max output-66K
Inputtexttext, vision
Released2025-09-292026-02-06

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryDeepSeek V3.2-ExpERNIE 5.0
Coding4.9 DeepSeek V3.2-Exp4.7 ERNIE 5.0
Agents21.3 DeepSeek V3.2-Exp20.7* ERNIE 5.0
Reasoning24.4 DeepSeek V3.2-Exp25.1 ERNIE 5.0
Knowledge & language19.8 DeepSeek V3.2-Exp17.8 ERNIE 5.0
Human preference47.7 DeepSeek V3.2-Exp51.9 ERNIE 5.0

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

DeepSeek V3.2-Exp leads on 3 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek V3.2-ExpERNIE 5.0
LMArena Elo14251446
AIME 202589.3%89.1%
HMMT 202583.6%79.6%
MMLU-Pro85%83.8%

FAQ

Is DeepSeek V3.2-Exp better than ERNIE 5.0?

ERNIE 5.0 scores 22.2 on the Respan Index (#118), ahead of DeepSeek V3.2-Exp at 21.8 (#121). DeepSeek V3.2-Exp leads on 3 of the 4 benchmarks both report.

Which has the larger context window?

Both accept 128K tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.