DeepSeek · mit

DeepSeek-V3.2

DeepSeek-V3.2 by DeepSeek appears in 2 sources with Reasoning at 41.8. Best read for Code quality, Coding, High intelligence.

CreatorDeepSeek

Release date2025-12-01

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank92ranking · source_rank

Reasoning41.8reasoning · index_reasoning

Math38.84math · index_math

Coding28.01coding · index_code

Research13.82research · index_search

Vision28.67multimodal · index_vision

Tool calling15.02tool_calling · index_tool_calling

Finance39.29domain · index_finance

Legal39.26domain · index_legal

Healthcare39.01domain · index_healthcare

GPQA82.4 %reasoning · gpqa_score

AIME 202593.1 %math · aime_2025_score

SWE-bench Verified73.1 %coding · swe_bench_verified_score

Code Arena550.35 %coding · coding_arena_score

Humanity Last Exam40.8 %reasoning · hle_score

BrowseComp51.4 %research · browsecomp_score

Toolathlon35.2 %tool_calling · toolathlon_score

Parameters685,000,000,000 paramsmodel · params

Arena Rating1,423.28metric

Arena Rank60metric

Vote Count45,034metric

Evidence

Citations and source overlap

Arena AILM Arena text leaderboard (overall) mirrored in the public leaderboard dataset.Retrieved 2026-05-20 LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is DeepSeek-V3.2 verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.