DDeepSeek · Active
DeepSeek V4.1 Flash
deepseek-flash family · launched 2026-09-10
MultimodalReasoningToolsStructuredOpen weightsAITopic score61.1Not yet ranked
Fast DeepSeek model for efficient chat, coding help, and agent loops
Evidence coverage45%2 evaluations · 1 institutions
Context / maximum output1M / 32.8ktokens
Cache / input / output$0.014 · $0.6 · $2.4USD per million tokens
Value / freshness45.8 / 86relative value · release freshness
What this model supports
Strengths by domain
Every result has a source
Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.
Coding1 results
AIHOT · CodingAIHOT61.90 scoreReading 61.9
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: AIHOT aggregateOpen evidenceKnowledge & instruction1 results
AIHOT · KnowledgeAIHOT62.00 scoreReading 62.0
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: AIHOT aggregateOpen evidenceHuman preference & indices2 results
AIHOT aggregate leaderboardAIHOT61.80 scoreReading 61.8
Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: AIHOT aggregateOpen evidenceAA IndexArtificial Analysis61.80 indexReading 42.7
Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: AIHOT aggregateOpen evidence