DeepSeek · mit

DeepSeek-V4-Flash-Max

DeepSeek-V4-Flash-Max by DeepSeek appears in 1 source with Reasoning at 51.86. Best read for Code quality, Long context, Low cost.

CreatorDeepSeek

Release date2026-04-23

Knowledge cutoffNot published

Context1M tokens

Input price$0.14/M tokens

Output price$0.28/M tokens

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank36ranking · source_rank

Reasoning51.86reasoning · index_reasoning

Math51.2math · index_math

Coding37.6coding · index_code

Research23.7research · index_search

Vision31.04multimodal · index_vision

Tool calling26.87tool_calling · index_tool_calling

Long context7.57long_context · index_long_context

Finance35domain · index_finance

Legal35.14domain · index_legal

Healthcare44.17domain · index_healthcare

GPQA88.1 %reasoning · gpqa_score

SWE-bench Verified79 %coding · swe_bench_verified_score

Code Arena1,126.85 %coding · coding_arena_score

Humanity Last Exam45.1 %reasoning · hle_score

SimpleQA34.1 %knowledge · simpleqa_score

BrowseComp73.2 %research · browsecomp_score

Toolathlon47.8 %tool_calling · toolathlon_score

MCP Atlas69 %tool_calling · mcp_atlas_score

SWE-bench Pro52.6 %coding · swe_bench_pro_score

Context1,048,576 tokenscontext · context

Speed175.82 c/sperformance · throughput

Latency22,592.92 msperformance · latency

Input price0.14 $/Mpricing · input_price

Output price0.28 $/Mpricing · output_price

Parameters284,000,000,000 paramsmodel · params

Evidence

Citations and source overlap

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-V4-Flash-Max 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.