LLM comparison · detail

DeepSeek V4 Pro 0813

Provider: DeepSeek

Model type: specialist Budget: open / self-run Use it for: large batches Use it for: coding Use it for: self-hosted stack

batch pick backed by current AA.

Verdict “DeepSeek V4 Pro 0813 has IQ 36 and input $1.32/M in the sources. Consider it for large batches, coding; for enterprise-governance, premium-agents, run a second benchmark before rollout.”

Snapshot summary

DeepSeek is a Chinese lab known for aggressive pricing, open-weight direction and models that pressure the big labs on serving cost. DeepSeek V4 Pro 0813 is the August revision of the Pro branch for coding, batch tasks and self-hosting. Compare it with V4.1 Flash using current measurements; the Pro label alone does not guarantee higher performance.

In this compare snapshot it is tagged mainly for batch, coding, self-hosted, with price tier free-open and context window is unavailable in verified data. The negative side matters too: watch enterprise-governance, premium-agents. Use the numbers below as the hard boundary, because this profile explains the model, it does not replace benchmark provenance.

Figures below, fetched from source artificial_analysis (fetched 2026-09-24T04:00:35Z).

Snapshot figures

self-hosted Budget provider-dependent

36 intelligence index artificial_analysis:deepseek-v4-pro

What this means

✓ Good for: large batches · coding · self-hosted stack

✗ Not for: company controls and audit · premium agents

Source and provenance

Data source: artificial_analysis
Fetched: 2026-09-24T04:00:35Z
Status per metric: price: artificial_analysis:deepseek-v4-pro; IQ: artificial_analysis:deepseek-v4-pro; Elo: curated_seed; Aider: curated_seed; DeepSWE: curated_seed

This page shows only verified data from the current snapshot.