Which is better, DeepSeek V4.1 Flash 1017 or Gemini 3.8 Flash?

Gemini 3.8 Flash scores higher on 3 of 7 shared quality measures, DeepSeek V4.1 Flash 1017 on 2. 2 measures are too close to call. DeepSeek V4.1 Flash 1017 costs about 65% less than Gemini 3.8 Flash on a blended price of $0.52 against $1.50 per million tokens. Which one is better for you depends on your task and budget, so test both on your own work.

Which is cheaper, DeepSeek V4.1 Flash 1017 or Gemini 3.8 Flash?

DeepSeek V4.1 Flash 1017 is cheaper on blended price: $0.52 per million tokens for DeepSeek V4.1 Flash 1017 against $1.50 for Gemini 3.8 Flash. For 100 chats of about 1,000 tokens in and 500 tokens back, that is about $0.09 for DeepSeek V4.1 Flash 1017 and $0.26 for Gemini 3.8 Flash.

Which can read longer documents, DeepSeek V4.1 Flash 1017 or Gemini 3.8 Flash?

DeepSeek V4.1 Flash 1017 has a context window of 1M tokens and Gemini 3.8 Flash has 1M tokens.

AI Rankings

DeepSeek V4.1 Flash 1017 vs Gemini 3.8 Flash: Scores, Price and Which to Choose

Side by side on every measure both models share: overall score, human votes, tests, price and context window. Close results are called too close to call.

Data updated 9 Nov 2026

Read the model pages for the full picture: DeepSeek V4.1 Flash 1017 and Gemini 3.8 Flash.

Side by side

A check mark shows the better side on each measure. Scores that are too close to call have no winner.

DeepSeek V4.1 Flash 1017 compared with Gemini 3.8 FlashDeepSeek V4.1 Flash 1017 against Gemini 3.8 Flash on 9 measures. DeepSeek V4.1 Flash 1017 is better on 3, Gemini 3.8 Flash on 3, 3 are too close to call, 0 have no data for one side.

DeepSeek V4.1 Flash 1017
Gemini 3.8 Flash

Epoch Capabilities IndexToo close to call
Combined score over many tests. Bar shows where it sits between the lowest and highest score we track.
DeepSeek V4.1 Flash 1017:
159.3
Gemini 3.8 Flash:
158.6
Arena web development ratingDeepSeek V4.1 Flash 1017 leads
Rating from head-to-head votes by people. Bar shows where it sits between the lowest and highest score we track.
DeepSeek V4.1 Flash 1017:
Better: 1664
Gemini 3.8 Flash:
1584
ARC-AGI-2Gemini 3.8 Flash leads
Visual puzzles where the AI must work out a new rule from a few examples and apply it.
DeepSeek V4.1 Flash 1017:
78.1%
Gemini 3.8 Flash:
Better: 89.2%
FrontierMath (Tiers 1-3)DeepSeek V4.1 Flash 1017 leads
Original, very hard maths problems written by mathematicians.
DeepSeek V4.1 Flash 1017:
Better: 71.2%
Gemini 3.8 Flash:
68.4%
GPQA DiamondGemini 3.8 Flash leads
Very hard multiple-choice science questions in biology, physics and chemistry, written by experts and designed so a quick web search does not give the answer.
DeepSeek V4.1 Flash 1017:
93.2%
Gemini 3.8 Flash:
Better: 95.4%
OTIS Mock AIMEToo close to call
Maths competition problems in the style of the US AIME exam, from the 2024 and 2025 sets.
DeepSeek V4.1 Flash 1017:
99.4%
Gemini 3.8 Flash:
98.9%
SimpleQA VerifiedGemini 3.8 Flash leads
Short factual questions that each have one correct answer.
DeepSeek V4.1 Flash 1017:
42.5%
Gemini 3.8 Flash:
Better: 69.7%
Blended price per million tokensDeepSeek V4.1 Flash 1017 costs less
Blended price: lower is better.
DeepSeek V4.1 Flash 1017:
Better: $0.52
Gemini 3.8 Flash:
$1.50
Context windowToo close to call
How much text it can read at once.
DeepSeek V4.1 Flash 1017:
1M tokens
Gemini 3.8 Flash:
1M tokens

Data updated 9 Nov 2026. Only measures that both models have are shown.

The numbers

DeepSeek V4.1 Flash 1017 against Gemini 3.8 Flash, measure by measure. A check mark shows the better side.
Measure	DeepSeek V4.1 Flash 1017	Gemini 3.8 Flash
Epoch Capabilities IndexToo close to call	159.3	158.6
Arena web development rating	1664	1584
ARC-AGI-2	78.1%	89.2%
FrontierMath (Tiers 1-3)	71.2%	68.4%
GPQA Diamond	93.2%	95.4%
OTIS Mock AIMEToo close to call	99.4%	98.9%
SimpleQA Verified	42.5%	69.7%
Blended price per million tokens	$0.52	$1.50
Context windowToo close to call	1M tokens	1M tokens

What it costs in everyday terms

Estimate for 100 chats of about 1,000 tokens in and 500 tokens back, from list prices. Your bill depends on how you use it.

100 chats with DeepSeek V4.1 Flash 1017: $0.09; Blended price $0.52 per million tokens.
100 chats with Gemini 3.8 Flash: $0.26; Blended price $1.50 per million tokens.

Who should pick which

Pick DeepSeek V4.1 Flash 1017 if these matter most

Arena web development rating: 1664 against 1584
FrontierMath (Tiers 1-3): 71.2% against 68.4%
Blended price per million tokens: $0.52 against $1.50

Pick Gemini 3.8 Flash if these matter most

ARC-AGI-2: 89.2% against 78.1%
GPQA Diamond: 95.4% against 93.2%
SimpleQA Verified: 69.7% against 42.5%

Too close to call: Epoch Capabilities Index, OTIS Mock AIME, Context window.

Scores come from tests and votes, not from your own work. Try both on a task you care about before you commit.

Go deeper

DeepSeek V4.1 Flash 1017: full page

Gemini 3.8 Flash: full page

Questions about this comparison

Which is better, DeepSeek V4.1 Flash 1017 or Gemini 3.8 Flash?: Gemini 3.8 Flash scores higher on 3 of 7 shared quality measures, DeepSeek V4.1 Flash 1017 on 2. 2 measures are too close to call. DeepSeek V4.1 Flash 1017 costs about 65% less than Gemini 3.8 Flash on a blended price of $0.52 against $1.50 per million tokens. Which one is better for you depends on your task and budget, so test both on your own work.
Which is cheaper, DeepSeek V4.1 Flash 1017 or Gemini 3.8 Flash?: DeepSeek V4.1 Flash 1017 is cheaper on blended price: $0.52 per million tokens for DeepSeek V4.1 Flash 1017 against $1.50 for Gemini 3.8 Flash. For 100 chats of about 1,000 tokens in and 500 tokens back, that is about $0.09 for DeepSeek V4.1 Flash 1017 and $0.26 for Gemini 3.8 Flash.
Which can read longer documents, DeepSeek V4.1 Flash 1017 or Gemini 3.8 Flash?: DeepSeek V4.1 Flash 1017 has a context window of 1M tokens and Gemini 3.8 Flash has 1M tokens.

Where this data comes from

Epoch AI: Benchmark data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0). We match models across sources, rank them and show them in charts. Scores are not changed. Epoch AI does not endorse this site.
Arena (formerly LMArena): Human-preference ratings: Arena (arena.ai) leaderboard dataset, CC BY 4.0. We keep the latest published ratings, match them to models from other sources and rank them. Ratings are not changed. Arena does not endorse this site.
LiteLLM model price list: Prices and context windows: LiteLLM model price list (github.com/BerriAI/litellm, MIT licence). We use the model maker's own price entry when there is one. Prices change often, so always confirm on the maker's site before you buy.

Newest data on this page: 9 Nov 2026. Prices are list prices and change often, so confirm on the maker's site before you buy. Sponsors never change a score or an order. How we calculate this · Report a mistake