#07DeepSeek· released 2026-08-12

DeepSeek: DeepSeek V4 Pro 0813.

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

View on OpenRouter ↗
Context
1.0M
Input $/1M
$1.12
Output $/1M
$3.36
Modality
text
Arena Elo
1591
LMArena — human blind votes
AA Index
65.0
Artificial Analysis composite
LiveBench
87.1
Contamination-resistant
GPQA
88.8%
Grad-level science reasoning
MMLU-Pro
88.9%
Broad knowledge
SWE-bench
76.4%
Real GitHub bugs (Verified)
Terminal-Bench
67.5%
Agentic shell tasks
ARC-AGI
33.5%
Abstract reasoning
Aider Polyglot
85.6%
Multi-language code editing
Speed
82 tok/s
Median output speed

Profile

DeepSeek: DeepSeek V4 Pro 0813 is DeepSeek's entry at position #7 on the current aggregated leaderboard. Its strongest signals are human preference voting, graduate-level science reasoning, real-world software engineering, and unattended agentic work. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard