The honest view from inside technical leadership
LLM Leaderboard · DeepSeek

DeepSeek V4.1 Flash

Benchmarks, pricing and rank for DeepSeek V4.1 Flash, with every score linked to the leaderboard that published it.

← All models

#2066.1CTO Index
Provider
DeepSeek
Weights
Open weights
License
MIT
Price $/M in / out
$0.15 / $0.60
Context window
1M
Benchmarks covered
5 of 5

October 17 checkpoint; the Text Arena rating is for the September 10 checkpoint.

Benchmark results

Terminal-Bench 4.1Agentic coding
38.5%
#24 of 41 tracked · source
WebDev ArenaCoding (human-judged)
1658
#21 of 44 tracked · source
ARC-AGI-2Reasoning
78.1%
#19 of 28 tracked · source
Text ArenaGeneral chat (human-judged)
1475
#23 of 40 tracked · source
ARC-AGI-3Interactive reasoning
0.2%
#18 of 19 tracked · source

Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works

Compare DeepSeek V4.1 Flash

Frequently asked questions

How good is DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash ranks #20 of 39 models on the Diary of a CTO Index with 66.1 points.

How much does DeepSeek V4.1 Flash cost?

DeepSeek V4.1 Flash lists at $0.15 / $0.60 per million input / output tokens.

What are DeepSeek V4.1 Flash's benchmark scores?

Terminal-Bench 4.1: 38.5%; WebDev Arena: 1658; ARC-AGI-2: 78.1%; Text Arena: 1475; ARC-AGI-3: 0.2%.

What is DeepSeek V4.1 Flash's context window?

DeepSeek V4.1 Flash supports a context window of 1M tokens.