RankingIA v0.6.1
EN

DeepSeek V4.1 Flash 1017open

DeepSeek

75.3#27 of 427 overall
Input / output
US$ 0,15 / US$ 0,60
US$ per 1M tokens
Context
1.0M
tokens
Release
10/17/2026
release date
Speed
163 tok/s
first token in 0.89 s

Family history

The 2 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table
ModelReleasedScoreRankAA Intel.Elo Arena
DeepSeek V4 Flash Latest08/01/202668.6#46—1432
DeepSeek V4.1 Flash 101710/17/202675.3#2732.51465

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
LiveBench weight 3 74.0 74% LiveBench
AA Intelligence Index weight 3 32.5 65% Artificial Analysis
Arena text (Elo) weight 2 1465 85% LMArena
Arena WebDev (Elo) weight 1 1665 89% LMArena
Arena vision (Elo) weight 0.5 1278 72% LMArena
Humanity's Last Exam weight 1 43.3 93% Artificial Analysis
Terminal-Bench weight 1 33.8 87% Artificial Analysis
Long-context reasoning 82.7 94% Artificial Analysis
LiveBench long agentic 40.9 71% LiveBench
LiveBench reasoning 89.1 58% LiveBench
LiveBench coding 96.0 92% LiveBench
LiveBench browser 67.2 55% LiveBench
LiveBench data analysis 79.5 74% LiveBench
LiveBench research 79.5 61% LiveBench
LiveBench design 83.4 92% LiveBench

By category

CategoryScoreRankMetrics
Agentic69.2#17LiveBench long agentic, Terminal-Bench
Coding76.9#5LiveBench coding, Arena WebDev (Elo)
Reasoning66.9#95LiveBench reasoning, Humanity's Last Exam
Data analysis62.1#9LiveBench data analysis
Research68.5#39LiveBench research, Long-context reasoning
Design76.9#4LiveBench design, Arena WebDev (Elo)
Browser use52.4#15LiveBench browser
Chat67.3#31Arena text (Elo)
Vision61.0#30Arena vision (Elo)

History

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.

Compare with other models

At the sources