Translate
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 Flash Vision

deepseek-flash family · launched 2026-08-21

MultimodalReasoningToolsStructuredOpen weights
AITopic score58.1#62 overall

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Evidence coverage90%4 evaluations · 1 institutions
Context / maximum output1M / 384ktokens
Cache / input / output$0.0069 · $0.22 · $0.65USD per million tokens
Value / freshness71.3 / 86relative value · release freshness
Product profile

What this model supports

Inputtext, image
Outputtext
Knowledge cutoffNot disclosed
WeightsOpen weights
Capability profile

Strengths by domain

Coding37.61 public results
Research & reasoning85.41 public results
Professional work63.31 public results
Knowledge & instruction69.21 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.

Coding1 results

LiveBench 2.0 · CodingLiveBench37.60 scoreReading 37.6

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

Configuration: LiveBench 2.0Open evidence

Research & reasoning1 results

LiveBench 2.0 · ResearchLiveBench85.40 scoreReading 85.4

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

Configuration: LiveBench 2.0Open evidence

Professional work1 results

LiveBench 2.0 · ProfessionalLiveBench63.30 scoreReading 63.3

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 2.0Open evidence

Knowledge & instruction1 results

LiveBench 2.0 · KnowledgeLiveBench69.20 scoreReading 69.2

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 2.0Open evidence

Human preference & indices2 results

LiveBenchLiveBench63.63 scoreReading 63.6

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

Configuration: LiveBench 2.0Open evidence
AA IndexArtificial Analysis63.63 indexReading 54.5

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

Configuration: LiveBench 2.0Open evidence
Same builder

More from DeepSeek