Skip to content
aiqbench

DeepSeek · model passport

DeepSeek: DeepSeek V3

deepseek-chat
  • Open weights
  • 684.5B params
  • 163,840 context
  • Released 2024-12-26(curated)
3/27axes covered
Best percentile
52.9GPQA Diamond
Cohort standing
45.1median 42.0

What the data says

Benchmarked on 3 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 23 percentile points between its best and worst axis — 52.9 pct on GPQA Diamond versus 29.9 pct on LiveBench.

  • GPQA Diamond52.9 pct71.2%Verify →
  • AIME (math)37.5 pct48.9%Verify →
  • LiveBench29.9 pct41.9%Verify →
  • OverallNot benchmarked
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot 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
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked
  • CodingNot benchmarked
  • Instruction followingNot benchmarked
  • Hard promptsNot 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-V3
Parameters684.5B
ArchitectureDeepseekV3ForCausalLM

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "deepseek-ai/DeepSeek-V3"
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-chat
Context length163,840 tokens
Max output16,384 tokens
Input price$0.32 per 1M tokens
Output price$0.89 per 1M tokens

API parameters this endpoint supports

Frequency penaltyLogit biasMax tokensMin-pPresence penaltyRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop-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-chat","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-chat stands at 45.1 (raw mean 40.1) — measured on 3 of 27 axes.

    standingtemplateVerify →

  • deepseek-chat stands at 45.1 versus a cohort median of 42 across 138 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 →