Skip to content
aiqbench

DeepSeek · model passport

DeepSeek: DeepSeek V4 Pro 0813

deepseek-v4-pro
  • Open weights
  • MIT licence
  • 1.65T params
  • 1,048,576 context
  • Released 2026-08-13(from model name)
13/27axes covered
Overall · LMArena
1,465#49 of 396
Best percentile
88.9Instruction following
Cohort standing
72.0median 59.8

What the data says

Benchmarked on 13 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 88.9 pct — Instruction following (1,461)
  • 87.9 pct — Overall (1,465)
  • 86.6 pct — Hard prompts (1,483)

Uneven: 43.4 percentile points between its best and worst axis — 88.9 pct on Instruction following versus 45.5 pct on Agent Arena.

  • Instruction following88.9 pct1,461Verify →
  • Overall87.9 pct1,465Verify →
  • Hard prompts86.6 pct1,483Verify →
  • GPQA Diamond86.4 pct90.9%Verify →
  • LiveBench85.9 pct71.6%Verify →
  • Coding84.7 pct1,505Verify →
  • SWE-bench Verified84.4 pct77.6%Verify →
  • AIME (math)83.5 pct96.7%Verify →
  • WebDev Arena79.1 pct1,582Verify →
  • Factuality Arena70.9 pct1,455Verify →
  • HHEM Hallucination (Vectara)59 pct91.4%Verify →
  • SimpleQA Verified58.5 pct47.0%Verify →
  • Agent Arena45.5 pct0.004Verify →
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositorydeepseek-ai/DeepSeek-V4-Pro-0813
Parameters1.65T
ArchitectureDeepseekV4ForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "deepseek-ai/DeepSeek-V4-Pro-0813"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDdeepseek/deepseek-v4-pro-0813
Context length1,048,576 tokens
Max output384,000 tokens
Input price$0.66 per 1M tokens
Cached input price$0.02 per 1M tokens
Output price$1.98 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin-pPresence penaltyReasoningReasoning effortRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop logprobsTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4-pro-0813","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • deepseek-v4-pro-high-20260813 stands at 72 (raw mean 77) — measured on 13 of 27 axes.

    standingtemplateVerify →

  • deepseek-v4-pro-high-20260813 stands at 72 versus a cohort median of 59.8 across 188 models released within 180 days — above the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →