DeepSeek Flash Low

DeepSeek Flash Low is a model from DeepSeek. It has 1 scored result in 1 category. It has no index.

  • Input: text
partialShows if the model has enough results for an index.
IndexOverall score out of 100.UnrankedMedian 50.7
CoverageShare of the index weight with results.5%
SpeedOutput tokens per second.—Median 62/s
First tokenSeconds to the first output token.N/AMedian 1.6 s
Input / 1MUS dollars per 1M input tokens.N/AMedian $0.6
Output / 1MUS dollars per 1M output tokens.N/AMedian $2.5
ContextMaximum tokens in one request.N/AMedian 262K
EloLMArena rating and rank.N/AMedian 1427

Capabilities

Score per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None countedN/A—
CodingCode writing and repair.None countedN/A—
ReasoningLogic problems and puzzles.None countedN/A—
MultimodalTasks with images and text.None countedN/A—
KnowledgeFacts and expert knowledge.None countedN/A—
MultilingualTasks in many languages.1 counted87.5—
InstructionTasks with strict rules in the prompt.None countedN/A—
MathMath problems.None countedN/A—

Results

1 counted
BenchmarkThe test name.ResultThe score from the source.PlacePlace among results on this benchmark.
EuroEval SwedishMultilingual70.8% ±0.67 / 186
EuroEval GermanMultilingual60.7% ±0.67 / 182
EuroEval SpanishMultilingual64.6% ±0.47 / 174
EuroEval PolishMultilingual62.7% ±0.511 / 205
EuroEval PortugueseMultilingual67.0% ±0.512 / 180
EuroEval FrenchMultilingual68.4% ±0.412 / 176
EuroEval DutchMultilingual64.3% ±0.412 / 167
EuroEval ItalianMultilingual66.0% ±0.416 / 172

Sources

BenchLM benchmark aggregationCC BY-NC 4.0 · Data from BenchLM.aiEuroEval, collected directlyMIT — the leaderboard site and its CSV routes are in the licensed repository

More from DeepSeek

All models
DeepSeek V4 Pro 081367.5DeepSeek V4.1 Flash67.0DeepSeek V4 Flash 073163.0DeepSeek V4 Pro 042358.5DeepSeek V3.2 (Thinking)49.1