Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check

Back to leaderboard

DeepSeek · Active

Deepseek V4.1 Flash 1017

deepseek-flash family · launched 2026-10-17

MultimodalReasoningToolsStructuredOpen weights

AITopic score75.7#14 overall

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

Evidence coverage100%8 evaluations · 2 institutions

Context / maximum output1M / 1Mtokens

Cache / input / output$0.006 · $0.3 · $1.2USD per million tokens

Value / freshness84.5 / 100relative value · release freshness

Product profile

What this model supports

Inputtext, image

Outputtext

Knowledge cutoff2025-05

WeightsOpen weights

Capability profile

Strengths by domain

Coding80.12 public results

Research & reasoning76.92 public results

Professional work67.72 public results

Knowledge & instruction72.72 public results

Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Coding2 results

LiveBench 2.0 · CodingLiveBench96.00 scoreReading 96.0

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AIHOT · CodingAIHOT64.10 scoreReading 64.1

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Research & reasoning2 results

LiveBench 2.0 · ResearchLiveBench89.10 scoreReading 89.1

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AIHOT · ResearchAIHOT64.60 scoreReading 64.6

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Professional work2 results

AIHOT · ProfessionalAIHOT68.90 scoreReading 68.9

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

LiveBench 2.0 · ProfessionalLiveBench66.45 scoreReading 66.5

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Knowledge & instruction2 results

LiveBench 2.0 · KnowledgeLiveBench79.50 scoreReading 79.5

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AIHOT · KnowledgeAIHOT65.80 scoreReading 65.8

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Human preference & indices3 results

AA IndexArtificial Analysis75.77 indexReading 91.0

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

LiveBenchLiveBench75.77 scoreReading 75.8

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AIHOT aggregate leaderboardAIHOT65.50 scoreReading 65.5

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence